Training in progress, step 375, checkpoint
Browse files- last-checkpoint/README.md +202 -0
- last-checkpoint/adapter_config.json +36 -0
- last-checkpoint/adapter_model.safetensors +3 -0
- last-checkpoint/merges.txt +0 -0
- last-checkpoint/optimizer.pt +3 -0
- last-checkpoint/rng_state.pth +3 -0
- last-checkpoint/scheduler.pt +3 -0
- last-checkpoint/special_tokens_map.json +30 -0
- last-checkpoint/tokenizer.json +0 -0
- last-checkpoint/tokenizer_config.json +23 -0
- last-checkpoint/trainer_state.json +2666 -0
- last-checkpoint/training_args.bin +3 -0
- last-checkpoint/vocab.json +0 -0
last-checkpoint/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: EleutherAI/gpt-neo-125m
|
3 |
+
library_name: peft
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.14.0
|
last-checkpoint/adapter_config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "EleutherAI/gpt-neo-125m",
|
5 |
+
"bias": "none",
|
6 |
+
"eva_config": null,
|
7 |
+
"exclude_modules": null,
|
8 |
+
"fan_in_fan_out": null,
|
9 |
+
"inference_mode": true,
|
10 |
+
"init_lora_weights": true,
|
11 |
+
"layer_replication": null,
|
12 |
+
"layers_pattern": null,
|
13 |
+
"layers_to_transform": null,
|
14 |
+
"loftq_config": {},
|
15 |
+
"lora_alpha": 16,
|
16 |
+
"lora_bias": false,
|
17 |
+
"lora_dropout": 0.05,
|
18 |
+
"megatron_config": null,
|
19 |
+
"megatron_core": "megatron.core",
|
20 |
+
"modules_to_save": null,
|
21 |
+
"peft_type": "LORA",
|
22 |
+
"r": 8,
|
23 |
+
"rank_pattern": {},
|
24 |
+
"revision": null,
|
25 |
+
"target_modules": [
|
26 |
+
"v_proj",
|
27 |
+
"q_proj",
|
28 |
+
"c_fc",
|
29 |
+
"out_proj",
|
30 |
+
"k_proj",
|
31 |
+
"c_proj"
|
32 |
+
],
|
33 |
+
"task_type": "CAUSAL_LM",
|
34 |
+
"use_dora": false,
|
35 |
+
"use_rslora": false
|
36 |
+
}
|
last-checkpoint/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b540a97127573040eb13b3e05008a286d1ccf3b6dd510f9592bd5bca56e8abca
|
3 |
+
size 5327496
|
last-checkpoint/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
last-checkpoint/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3584364385ee92d69d793759412266f118b58a4c6c21b7df6c8e77df372d6147
|
3 |
+
size 2857850
|
last-checkpoint/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6a7b7eb2fe4472278ab50b6b7d479ddcfad70595ae73db4f92f3f6acbfe9eea0
|
3 |
+
size 14244
|
last-checkpoint/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4bf304e342001350c82d6970cec50fb92a4329a84dcb76ae8031bca03ca92aa9
|
3 |
+
size 1064
|
last-checkpoint/special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|endoftext|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|endoftext|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<|endoftext|>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
last-checkpoint/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
last-checkpoint/tokenizer_config.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"50256": {
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
}
|
13 |
+
},
|
14 |
+
"bos_token": "<|endoftext|>",
|
15 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
|
16 |
+
"clean_up_tokenization_spaces": true,
|
17 |
+
"eos_token": "<|endoftext|>",
|
18 |
+
"errors": "replace",
|
19 |
+
"model_max_length": 2048,
|
20 |
+
"pad_token": "<|endoftext|>",
|
21 |
+
"tokenizer_class": "GPT2Tokenizer",
|
22 |
+
"unk_token": "<|endoftext|>"
|
23 |
+
}
|
last-checkpoint/trainer_state.json
ADDED
@@ -0,0 +1,2666 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.22661177625863957,
|
5 |
+
"eval_steps": 375,
|
6 |
+
"global_step": 375,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0006042980700230389,
|
13 |
+
"grad_norm": 0.6723806858062744,
|
14 |
+
"learning_rate": 2e-05,
|
15 |
+
"loss": 0.7525,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.0012085961400460777,
|
20 |
+
"grad_norm": 0.6356388926506042,
|
21 |
+
"learning_rate": 4e-05,
|
22 |
+
"loss": 1.4247,
|
23 |
+
"step": 2
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.0018128942100691166,
|
27 |
+
"grad_norm": 0.8352575898170471,
|
28 |
+
"learning_rate": 6e-05,
|
29 |
+
"loss": 2.0536,
|
30 |
+
"step": 3
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.0024171922800921555,
|
34 |
+
"grad_norm": 0.8536075353622437,
|
35 |
+
"learning_rate": 8e-05,
|
36 |
+
"loss": 2.207,
|
37 |
+
"step": 4
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.003021490350115194,
|
41 |
+
"grad_norm": 0.8931390047073364,
|
42 |
+
"learning_rate": 0.0001,
|
43 |
+
"loss": 2.3663,
|
44 |
+
"step": 5
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.0036257884201382332,
|
48 |
+
"grad_norm": 0.9978416562080383,
|
49 |
+
"learning_rate": 0.00012,
|
50 |
+
"loss": 2.3864,
|
51 |
+
"step": 6
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.004230086490161272,
|
55 |
+
"grad_norm": 0.9493173956871033,
|
56 |
+
"learning_rate": 0.00014,
|
57 |
+
"loss": 2.2914,
|
58 |
+
"step": 7
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.004834384560184311,
|
62 |
+
"grad_norm": 0.9359995722770691,
|
63 |
+
"learning_rate": 0.00016,
|
64 |
+
"loss": 2.3039,
|
65 |
+
"step": 8
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.00543868263020735,
|
69 |
+
"grad_norm": 1.0341345071792603,
|
70 |
+
"learning_rate": 0.00018,
|
71 |
+
"loss": 2.4413,
|
72 |
+
"step": 9
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.006042980700230388,
|
76 |
+
"grad_norm": 1.0705313682556152,
|
77 |
+
"learning_rate": 0.0002,
|
78 |
+
"loss": 2.4622,
|
79 |
+
"step": 10
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.006647278770253427,
|
83 |
+
"grad_norm": 1.157464861869812,
|
84 |
+
"learning_rate": 0.00019999977772170748,
|
85 |
+
"loss": 2.338,
|
86 |
+
"step": 11
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.0072515768402764665,
|
90 |
+
"grad_norm": 1.0905333757400513,
|
91 |
+
"learning_rate": 0.00019999911088781805,
|
92 |
+
"loss": 2.2185,
|
93 |
+
"step": 12
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.007855874910299505,
|
97 |
+
"grad_norm": 1.2449381351470947,
|
98 |
+
"learning_rate": 0.0001999979995012962,
|
99 |
+
"loss": 2.1223,
|
100 |
+
"step": 13
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.008460172980322544,
|
104 |
+
"grad_norm": 1.2261898517608643,
|
105 |
+
"learning_rate": 0.00019999644356708261,
|
106 |
+
"loss": 2.1547,
|
107 |
+
"step": 14
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.009064471050345583,
|
111 |
+
"grad_norm": 1.2600151300430298,
|
112 |
+
"learning_rate": 0.00019999444309209432,
|
113 |
+
"loss": 2.1783,
|
114 |
+
"step": 15
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.009668769120368622,
|
118 |
+
"grad_norm": 1.3068581819534302,
|
119 |
+
"learning_rate": 0.0001999919980852246,
|
120 |
+
"loss": 2.1884,
|
121 |
+
"step": 16
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.010273067190391661,
|
125 |
+
"grad_norm": 1.5525509119033813,
|
126 |
+
"learning_rate": 0.00019998910855734288,
|
127 |
+
"loss": 2.1489,
|
128 |
+
"step": 17
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.0108773652604147,
|
132 |
+
"grad_norm": 1.5854105949401855,
|
133 |
+
"learning_rate": 0.0001999857745212947,
|
134 |
+
"loss": 2.0207,
|
135 |
+
"step": 18
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.01148166333043774,
|
139 |
+
"grad_norm": 1.6069377660751343,
|
140 |
+
"learning_rate": 0.00019998199599190178,
|
141 |
+
"loss": 2.1773,
|
142 |
+
"step": 19
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.012085961400460777,
|
146 |
+
"grad_norm": 1.8314810991287231,
|
147 |
+
"learning_rate": 0.0001999777729859618,
|
148 |
+
"loss": 2.1165,
|
149 |
+
"step": 20
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.012690259470483816,
|
153 |
+
"grad_norm": 1.5624139308929443,
|
154 |
+
"learning_rate": 0.00019997310552224846,
|
155 |
+
"loss": 2.0546,
|
156 |
+
"step": 21
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.013294557540506855,
|
160 |
+
"grad_norm": 1.526838779449463,
|
161 |
+
"learning_rate": 0.00019996799362151122,
|
162 |
+
"loss": 2.17,
|
163 |
+
"step": 22
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.013898855610529894,
|
167 |
+
"grad_norm": 2.1960701942443848,
|
168 |
+
"learning_rate": 0.00019996243730647538,
|
169 |
+
"loss": 2.2203,
|
170 |
+
"step": 23
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.014503153680552933,
|
174 |
+
"grad_norm": 2.307544708251953,
|
175 |
+
"learning_rate": 0.00019995643660184191,
|
176 |
+
"loss": 2.1815,
|
177 |
+
"step": 24
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.015107451750575972,
|
181 |
+
"grad_norm": 2.294649362564087,
|
182 |
+
"learning_rate": 0.00019994999153428737,
|
183 |
+
"loss": 2.2256,
|
184 |
+
"step": 25
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.01571174982059901,
|
188 |
+
"grad_norm": 2.0167179107666016,
|
189 |
+
"learning_rate": 0.00019994310213246368,
|
190 |
+
"loss": 2.378,
|
191 |
+
"step": 26
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.01631604789062205,
|
195 |
+
"grad_norm": 1.8471157550811768,
|
196 |
+
"learning_rate": 0.00019993576842699816,
|
197 |
+
"loss": 2.2643,
|
198 |
+
"step": 27
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.016920345960645088,
|
202 |
+
"grad_norm": 2.103811502456665,
|
203 |
+
"learning_rate": 0.0001999279904504933,
|
204 |
+
"loss": 2.4134,
|
205 |
+
"step": 28
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.017524644030668127,
|
209 |
+
"grad_norm": 2.363506555557251,
|
210 |
+
"learning_rate": 0.00019991976823752653,
|
211 |
+
"loss": 2.3607,
|
212 |
+
"step": 29
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.018128942100691166,
|
216 |
+
"grad_norm": 2.0845320224761963,
|
217 |
+
"learning_rate": 0.00019991110182465032,
|
218 |
+
"loss": 2.4767,
|
219 |
+
"step": 30
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.018733240170714205,
|
223 |
+
"grad_norm": 2.4435393810272217,
|
224 |
+
"learning_rate": 0.00019990199125039174,
|
225 |
+
"loss": 2.3495,
|
226 |
+
"step": 31
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.019337538240737244,
|
230 |
+
"grad_norm": 2.0392420291900635,
|
231 |
+
"learning_rate": 0.00019989243655525247,
|
232 |
+
"loss": 2.3409,
|
233 |
+
"step": 32
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.019941836310760283,
|
237 |
+
"grad_norm": 2.0392611026763916,
|
238 |
+
"learning_rate": 0.00019988243778170853,
|
239 |
+
"loss": 2.2221,
|
240 |
+
"step": 33
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.020546134380783322,
|
244 |
+
"grad_norm": 2.322539806365967,
|
245 |
+
"learning_rate": 0.0001998719949742101,
|
246 |
+
"loss": 2.4324,
|
247 |
+
"step": 34
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.02115043245080636,
|
251 |
+
"grad_norm": 2.2848479747772217,
|
252 |
+
"learning_rate": 0.0001998611081791814,
|
253 |
+
"loss": 2.411,
|
254 |
+
"step": 35
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.0217547305208294,
|
258 |
+
"grad_norm": 2.3438031673431396,
|
259 |
+
"learning_rate": 0.00019984977744502038,
|
260 |
+
"loss": 2.3022,
|
261 |
+
"step": 36
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.02235902859085244,
|
265 |
+
"grad_norm": 2.3946008682250977,
|
266 |
+
"learning_rate": 0.00019983800282209857,
|
267 |
+
"loss": 2.4329,
|
268 |
+
"step": 37
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.02296332666087548,
|
272 |
+
"grad_norm": 2.265860080718994,
|
273 |
+
"learning_rate": 0.00019982578436276082,
|
274 |
+
"loss": 2.2641,
|
275 |
+
"step": 38
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.023567624730898514,
|
279 |
+
"grad_norm": 3.028747320175171,
|
280 |
+
"learning_rate": 0.00019981312212132512,
|
281 |
+
"loss": 2.2929,
|
282 |
+
"step": 39
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.024171922800921553,
|
286 |
+
"grad_norm": 2.5112571716308594,
|
287 |
+
"learning_rate": 0.00019980001615408228,
|
288 |
+
"loss": 2.4233,
|
289 |
+
"step": 40
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.024776220870944592,
|
293 |
+
"grad_norm": 2.5553221702575684,
|
294 |
+
"learning_rate": 0.00019978646651929572,
|
295 |
+
"loss": 2.5443,
|
296 |
+
"step": 41
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.02538051894096763,
|
300 |
+
"grad_norm": 2.7476682662963867,
|
301 |
+
"learning_rate": 0.00019977247327720128,
|
302 |
+
"loss": 2.4841,
|
303 |
+
"step": 42
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.02598481701099067,
|
307 |
+
"grad_norm": 2.6699960231781006,
|
308 |
+
"learning_rate": 0.0001997580364900068,
|
309 |
+
"loss": 2.5442,
|
310 |
+
"step": 43
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.02658911508101371,
|
314 |
+
"grad_norm": 2.905996561050415,
|
315 |
+
"learning_rate": 0.000199743156221892,
|
316 |
+
"loss": 2.7954,
|
317 |
+
"step": 44
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.02719341315103675,
|
321 |
+
"grad_norm": 3.1173646450042725,
|
322 |
+
"learning_rate": 0.00019972783253900808,
|
323 |
+
"loss": 2.5903,
|
324 |
+
"step": 45
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.027797711221059788,
|
328 |
+
"grad_norm": 3.142016887664795,
|
329 |
+
"learning_rate": 0.00019971206550947748,
|
330 |
+
"loss": 2.7681,
|
331 |
+
"step": 46
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.028402009291082827,
|
335 |
+
"grad_norm": 3.2653255462646484,
|
336 |
+
"learning_rate": 0.00019969585520339354,
|
337 |
+
"loss": 2.8531,
|
338 |
+
"step": 47
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.029006307361105866,
|
342 |
+
"grad_norm": 4.3081583976745605,
|
343 |
+
"learning_rate": 0.0001996792016928203,
|
344 |
+
"loss": 3.074,
|
345 |
+
"step": 48
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.029610605431128905,
|
349 |
+
"grad_norm": 7.22359037399292,
|
350 |
+
"learning_rate": 0.00019966210505179197,
|
351 |
+
"loss": 3.7639,
|
352 |
+
"step": 49
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 0.030214903501151944,
|
356 |
+
"grad_norm": 15.731882095336914,
|
357 |
+
"learning_rate": 0.00019964456535631286,
|
358 |
+
"loss": 4.334,
|
359 |
+
"step": 50
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.030819201571174983,
|
363 |
+
"grad_norm": 2.968768835067749,
|
364 |
+
"learning_rate": 0.0001996265826843568,
|
365 |
+
"loss": 0.7182,
|
366 |
+
"step": 51
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.03142349964119802,
|
370 |
+
"grad_norm": 3.0781517028808594,
|
371 |
+
"learning_rate": 0.00019960815711586696,
|
372 |
+
"loss": 1.2886,
|
373 |
+
"step": 52
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.03202779771122106,
|
377 |
+
"grad_norm": 3.273003101348877,
|
378 |
+
"learning_rate": 0.00019958928873275539,
|
379 |
+
"loss": 1.9765,
|
380 |
+
"step": 53
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.0326320957812441,
|
384 |
+
"grad_norm": 2.7970402240753174,
|
385 |
+
"learning_rate": 0.00019956997761890277,
|
386 |
+
"loss": 1.9967,
|
387 |
+
"step": 54
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.033236393851267136,
|
391 |
+
"grad_norm": 2.716160774230957,
|
392 |
+
"learning_rate": 0.00019955022386015792,
|
393 |
+
"loss": 2.1967,
|
394 |
+
"step": 55
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 0.033840691921290175,
|
398 |
+
"grad_norm": 2.9746975898742676,
|
399 |
+
"learning_rate": 0.00019953002754433743,
|
400 |
+
"loss": 2.313,
|
401 |
+
"step": 56
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.034444989991313214,
|
405 |
+
"grad_norm": 2.6240665912628174,
|
406 |
+
"learning_rate": 0.00019950938876122542,
|
407 |
+
"loss": 2.3107,
|
408 |
+
"step": 57
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 0.03504928806133625,
|
412 |
+
"grad_norm": 2.2789065837860107,
|
413 |
+
"learning_rate": 0.00019948830760257291,
|
414 |
+
"loss": 2.1248,
|
415 |
+
"step": 58
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 0.03565358613135929,
|
419 |
+
"grad_norm": 2.2027852535247803,
|
420 |
+
"learning_rate": 0.0001994667841620976,
|
421 |
+
"loss": 2.3983,
|
422 |
+
"step": 59
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.03625788420138233,
|
426 |
+
"grad_norm": 2.5889904499053955,
|
427 |
+
"learning_rate": 0.00019944481853548335,
|
428 |
+
"loss": 2.3289,
|
429 |
+
"step": 60
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.03686218227140537,
|
433 |
+
"grad_norm": 2.0383386611938477,
|
434 |
+
"learning_rate": 0.00019942241082037982,
|
435 |
+
"loss": 2.4328,
|
436 |
+
"step": 61
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 0.03746648034142841,
|
440 |
+
"grad_norm": 1.9245140552520752,
|
441 |
+
"learning_rate": 0.00019939956111640197,
|
442 |
+
"loss": 2.25,
|
443 |
+
"step": 62
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.03807077841145145,
|
447 |
+
"grad_norm": 2.250455141067505,
|
448 |
+
"learning_rate": 0.00019937626952512964,
|
449 |
+
"loss": 2.4095,
|
450 |
+
"step": 63
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 0.03867507648147449,
|
454 |
+
"grad_norm": 1.8156126737594604,
|
455 |
+
"learning_rate": 0.0001993525361501072,
|
456 |
+
"loss": 2.1022,
|
457 |
+
"step": 64
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 0.03927937455149753,
|
461 |
+
"grad_norm": 2.0205323696136475,
|
462 |
+
"learning_rate": 0.00019932836109684286,
|
463 |
+
"loss": 2.1322,
|
464 |
+
"step": 65
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.039883672621520566,
|
468 |
+
"grad_norm": 1.8734694719314575,
|
469 |
+
"learning_rate": 0.00019930374447280845,
|
470 |
+
"loss": 1.9571,
|
471 |
+
"step": 66
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.040487970691543605,
|
475 |
+
"grad_norm": 2.0151290893554688,
|
476 |
+
"learning_rate": 0.00019927868638743875,
|
477 |
+
"loss": 1.9123,
|
478 |
+
"step": 67
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 0.041092268761566644,
|
482 |
+
"grad_norm": 2.1093060970306396,
|
483 |
+
"learning_rate": 0.0001992531869521312,
|
484 |
+
"loss": 2.0122,
|
485 |
+
"step": 68
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 0.04169656683158968,
|
489 |
+
"grad_norm": 2.0080783367156982,
|
490 |
+
"learning_rate": 0.00019922724628024515,
|
491 |
+
"loss": 2.013,
|
492 |
+
"step": 69
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 0.04230086490161272,
|
496 |
+
"grad_norm": 2.097050428390503,
|
497 |
+
"learning_rate": 0.0001992008644871016,
|
498 |
+
"loss": 2.0439,
|
499 |
+
"step": 70
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 0.04290516297163576,
|
503 |
+
"grad_norm": 1.9204063415527344,
|
504 |
+
"learning_rate": 0.00019917404168998256,
|
505 |
+
"loss": 1.8985,
|
506 |
+
"step": 71
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.0435094610416588,
|
510 |
+
"grad_norm": 1.9057285785675049,
|
511 |
+
"learning_rate": 0.0001991467780081305,
|
512 |
+
"loss": 2.0124,
|
513 |
+
"step": 72
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.04411375911168184,
|
517 |
+
"grad_norm": 1.9287506341934204,
|
518 |
+
"learning_rate": 0.00019911907356274795,
|
519 |
+
"loss": 2.1344,
|
520 |
+
"step": 73
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 0.04471805718170488,
|
524 |
+
"grad_norm": 1.8858532905578613,
|
525 |
+
"learning_rate": 0.00019909092847699683,
|
526 |
+
"loss": 2.1661,
|
527 |
+
"step": 74
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 0.04532235525172792,
|
531 |
+
"grad_norm": 2.1366336345672607,
|
532 |
+
"learning_rate": 0.00019906234287599798,
|
533 |
+
"loss": 2.2085,
|
534 |
+
"step": 75
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.04592665332175096,
|
538 |
+
"grad_norm": 1.9908347129821777,
|
539 |
+
"learning_rate": 0.00019903331688683057,
|
540 |
+
"loss": 2.1772,
|
541 |
+
"step": 76
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 0.04653095139177399,
|
545 |
+
"grad_norm": 2.1487462520599365,
|
546 |
+
"learning_rate": 0.00019900385063853154,
|
547 |
+
"loss": 2.2814,
|
548 |
+
"step": 77
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 0.04713524946179703,
|
552 |
+
"grad_norm": 2.083444595336914,
|
553 |
+
"learning_rate": 0.00019897394426209505,
|
554 |
+
"loss": 2.2921,
|
555 |
+
"step": 78
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.04773954753182007,
|
559 |
+
"grad_norm": 2.356961250305176,
|
560 |
+
"learning_rate": 0.00019894359789047187,
|
561 |
+
"loss": 2.3103,
|
562 |
+
"step": 79
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 0.048343845601843106,
|
566 |
+
"grad_norm": 2.109005928039551,
|
567 |
+
"learning_rate": 0.00019891281165856873,
|
568 |
+
"loss": 2.2682,
|
569 |
+
"step": 80
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 0.048948143671866146,
|
573 |
+
"grad_norm": 2.2167046070098877,
|
574 |
+
"learning_rate": 0.00019888158570324795,
|
575 |
+
"loss": 2.3838,
|
576 |
+
"step": 81
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 0.049552441741889185,
|
580 |
+
"grad_norm": 2.2872414588928223,
|
581 |
+
"learning_rate": 0.0001988499201633265,
|
582 |
+
"loss": 2.2507,
|
583 |
+
"step": 82
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 0.050156739811912224,
|
587 |
+
"grad_norm": 2.393831253051758,
|
588 |
+
"learning_rate": 0.00019881781517957562,
|
589 |
+
"loss": 2.1679,
|
590 |
+
"step": 83
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 0.05076103788193526,
|
594 |
+
"grad_norm": 2.3482563495635986,
|
595 |
+
"learning_rate": 0.0001987852708947202,
|
596 |
+
"loss": 2.1021,
|
597 |
+
"step": 84
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.0513653359519583,
|
601 |
+
"grad_norm": 2.3528244495391846,
|
602 |
+
"learning_rate": 0.00019875228745343794,
|
603 |
+
"loss": 2.3149,
|
604 |
+
"step": 85
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 0.05196963402198134,
|
608 |
+
"grad_norm": 2.345458745956421,
|
609 |
+
"learning_rate": 0.0001987188650023589,
|
610 |
+
"loss": 2.2611,
|
611 |
+
"step": 86
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 0.05257393209200438,
|
615 |
+
"grad_norm": 2.626271963119507,
|
616 |
+
"learning_rate": 0.0001986850036900648,
|
617 |
+
"loss": 2.2347,
|
618 |
+
"step": 87
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 0.05317823016202742,
|
622 |
+
"grad_norm": 3.3226706981658936,
|
623 |
+
"learning_rate": 0.00019865070366708836,
|
624 |
+
"loss": 2.2486,
|
625 |
+
"step": 88
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 0.05378252823205046,
|
629 |
+
"grad_norm": 2.9476661682128906,
|
630 |
+
"learning_rate": 0.00019861596508591255,
|
631 |
+
"loss": 2.3295,
|
632 |
+
"step": 89
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 0.0543868263020735,
|
636 |
+
"grad_norm": 2.7701926231384277,
|
637 |
+
"learning_rate": 0.00019858078810097002,
|
638 |
+
"loss": 2.3878,
|
639 |
+
"step": 90
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.054991124372096536,
|
643 |
+
"grad_norm": 2.8630998134613037,
|
644 |
+
"learning_rate": 0.00019854517286864245,
|
645 |
+
"loss": 2.3634,
|
646 |
+
"step": 91
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 0.055595422442119576,
|
650 |
+
"grad_norm": 2.862698554992676,
|
651 |
+
"learning_rate": 0.0001985091195472596,
|
652 |
+
"loss": 2.4529,
|
653 |
+
"step": 92
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 0.056199720512142615,
|
657 |
+
"grad_norm": 2.695298433303833,
|
658 |
+
"learning_rate": 0.0001984726282970989,
|
659 |
+
"loss": 2.3837,
|
660 |
+
"step": 93
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 0.056804018582165654,
|
664 |
+
"grad_norm": 2.9406235218048096,
|
665 |
+
"learning_rate": 0.0001984356992803847,
|
666 |
+
"loss": 2.4949,
|
667 |
+
"step": 94
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 0.05740831665218869,
|
671 |
+
"grad_norm": 2.9532742500305176,
|
672 |
+
"learning_rate": 0.00019839833266128724,
|
673 |
+
"loss": 2.4258,
|
674 |
+
"step": 95
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 0.05801261472221173,
|
678 |
+
"grad_norm": 3.499074935913086,
|
679 |
+
"learning_rate": 0.00019836052860592237,
|
680 |
+
"loss": 2.6488,
|
681 |
+
"step": 96
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 0.05861691279223477,
|
685 |
+
"grad_norm": 4.071224212646484,
|
686 |
+
"learning_rate": 0.0001983222872823505,
|
687 |
+
"loss": 2.6862,
|
688 |
+
"step": 97
|
689 |
+
},
|
690 |
+
{
|
691 |
+
"epoch": 0.05922121086225781,
|
692 |
+
"grad_norm": 4.09813928604126,
|
693 |
+
"learning_rate": 0.00019828360886057594,
|
694 |
+
"loss": 2.8312,
|
695 |
+
"step": 98
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 0.05982550893228085,
|
699 |
+
"grad_norm": 6.380131721496582,
|
700 |
+
"learning_rate": 0.00019824449351254616,
|
701 |
+
"loss": 3.0643,
|
702 |
+
"step": 99
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 0.06042980700230389,
|
706 |
+
"grad_norm": 17.392900466918945,
|
707 |
+
"learning_rate": 0.00019820494141215104,
|
708 |
+
"loss": 4.2204,
|
709 |
+
"step": 100
|
710 |
+
},
|
711 |
+
{
|
712 |
+
"epoch": 0.06103410507232693,
|
713 |
+
"grad_norm": 2.4286563396453857,
|
714 |
+
"learning_rate": 0.000198164952735222,
|
715 |
+
"loss": 0.687,
|
716 |
+
"step": 101
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 0.061638403142349966,
|
720 |
+
"grad_norm": 2.4470341205596924,
|
721 |
+
"learning_rate": 0.00019812452765953135,
|
722 |
+
"loss": 1.4129,
|
723 |
+
"step": 102
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 0.062242701212373006,
|
727 |
+
"grad_norm": 2.4300434589385986,
|
728 |
+
"learning_rate": 0.00019808366636479147,
|
729 |
+
"loss": 1.8864,
|
730 |
+
"step": 103
|
731 |
+
},
|
732 |
+
{
|
733 |
+
"epoch": 0.06284699928239604,
|
734 |
+
"grad_norm": 2.781144380569458,
|
735 |
+
"learning_rate": 0.00019804236903265388,
|
736 |
+
"loss": 2.2268,
|
737 |
+
"step": 104
|
738 |
+
},
|
739 |
+
{
|
740 |
+
"epoch": 0.06345129735241908,
|
741 |
+
"grad_norm": 2.7623088359832764,
|
742 |
+
"learning_rate": 0.00019800063584670863,
|
743 |
+
"loss": 2.2182,
|
744 |
+
"step": 105
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 0.06405559542244212,
|
748 |
+
"grad_norm": 2.4676239490509033,
|
749 |
+
"learning_rate": 0.00019795846699248332,
|
750 |
+
"loss": 2.3688,
|
751 |
+
"step": 106
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"epoch": 0.06465989349246516,
|
755 |
+
"grad_norm": 2.56716251373291,
|
756 |
+
"learning_rate": 0.00019791586265744237,
|
757 |
+
"loss": 2.3069,
|
758 |
+
"step": 107
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 0.0652641915624882,
|
762 |
+
"grad_norm": 2.625476837158203,
|
763 |
+
"learning_rate": 0.00019787282303098617,
|
764 |
+
"loss": 2.4915,
|
765 |
+
"step": 108
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 0.06586848963251124,
|
769 |
+
"grad_norm": 2.214947462081909,
|
770 |
+
"learning_rate": 0.0001978293483044502,
|
771 |
+
"loss": 2.4314,
|
772 |
+
"step": 109
|
773 |
+
},
|
774 |
+
{
|
775 |
+
"epoch": 0.06647278770253427,
|
776 |
+
"grad_norm": 2.3063435554504395,
|
777 |
+
"learning_rate": 0.00019778543867110426,
|
778 |
+
"loss": 2.3165,
|
779 |
+
"step": 110
|
780 |
+
},
|
781 |
+
{
|
782 |
+
"epoch": 0.06707708577255732,
|
783 |
+
"grad_norm": 2.1222662925720215,
|
784 |
+
"learning_rate": 0.00019774109432615147,
|
785 |
+
"loss": 2.3531,
|
786 |
+
"step": 111
|
787 |
+
},
|
788 |
+
{
|
789 |
+
"epoch": 0.06768138384258035,
|
790 |
+
"grad_norm": 2.2197558879852295,
|
791 |
+
"learning_rate": 0.00019769631546672756,
|
792 |
+
"loss": 2.2317,
|
793 |
+
"step": 112
|
794 |
+
},
|
795 |
+
{
|
796 |
+
"epoch": 0.0682856819126034,
|
797 |
+
"grad_norm": 2.209230661392212,
|
798 |
+
"learning_rate": 0.00019765110229189988,
|
799 |
+
"loss": 2.108,
|
800 |
+
"step": 113
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 0.06888997998262643,
|
804 |
+
"grad_norm": 2.125019073486328,
|
805 |
+
"learning_rate": 0.00019760545500266657,
|
806 |
+
"loss": 1.9513,
|
807 |
+
"step": 114
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 0.06949427805264947,
|
811 |
+
"grad_norm": 2.7421507835388184,
|
812 |
+
"learning_rate": 0.00019755937380195568,
|
813 |
+
"loss": 2.0994,
|
814 |
+
"step": 115
|
815 |
+
},
|
816 |
+
{
|
817 |
+
"epoch": 0.0700985761226725,
|
818 |
+
"grad_norm": 2.6599299907684326,
|
819 |
+
"learning_rate": 0.00019751285889462423,
|
820 |
+
"loss": 1.9108,
|
821 |
+
"step": 116
|
822 |
+
},
|
823 |
+
{
|
824 |
+
"epoch": 0.07070287419269555,
|
825 |
+
"grad_norm": 2.2113850116729736,
|
826 |
+
"learning_rate": 0.0001974659104874573,
|
827 |
+
"loss": 1.857,
|
828 |
+
"step": 117
|
829 |
+
},
|
830 |
+
{
|
831 |
+
"epoch": 0.07130717226271858,
|
832 |
+
"grad_norm": 2.392446279525757,
|
833 |
+
"learning_rate": 0.0001974185287891671,
|
834 |
+
"loss": 1.971,
|
835 |
+
"step": 118
|
836 |
+
},
|
837 |
+
{
|
838 |
+
"epoch": 0.07191147033274163,
|
839 |
+
"grad_norm": 2.2785661220550537,
|
840 |
+
"learning_rate": 0.0001973707140103921,
|
841 |
+
"loss": 1.9599,
|
842 |
+
"step": 119
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 0.07251576840276466,
|
846 |
+
"grad_norm": 2.4346420764923096,
|
847 |
+
"learning_rate": 0.00019732246636369605,
|
848 |
+
"loss": 2.0515,
|
849 |
+
"step": 120
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.07312006647278771,
|
853 |
+
"grad_norm": 2.22165846824646,
|
854 |
+
"learning_rate": 0.00019727378606356703,
|
855 |
+
"loss": 2.0886,
|
856 |
+
"step": 121
|
857 |
+
},
|
858 |
+
{
|
859 |
+
"epoch": 0.07372436454281074,
|
860 |
+
"grad_norm": 2.303600549697876,
|
861 |
+
"learning_rate": 0.00019722467332641656,
|
862 |
+
"loss": 2.0801,
|
863 |
+
"step": 122
|
864 |
+
},
|
865 |
+
{
|
866 |
+
"epoch": 0.07432866261283377,
|
867 |
+
"grad_norm": 2.389984130859375,
|
868 |
+
"learning_rate": 0.00019717512837057855,
|
869 |
+
"loss": 2.1252,
|
870 |
+
"step": 123
|
871 |
+
},
|
872 |
+
{
|
873 |
+
"epoch": 0.07493296068285682,
|
874 |
+
"grad_norm": 2.2050936222076416,
|
875 |
+
"learning_rate": 0.0001971251514163083,
|
876 |
+
"loss": 2.0506,
|
877 |
+
"step": 124
|
878 |
+
},
|
879 |
+
{
|
880 |
+
"epoch": 0.07553725875287985,
|
881 |
+
"grad_norm": 2.605313539505005,
|
882 |
+
"learning_rate": 0.0001970747426857817,
|
883 |
+
"loss": 2.1459,
|
884 |
+
"step": 125
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 0.0761415568229029,
|
888 |
+
"grad_norm": 2.3666372299194336,
|
889 |
+
"learning_rate": 0.00019702390240309404,
|
890 |
+
"loss": 2.217,
|
891 |
+
"step": 126
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 0.07674585489292593,
|
895 |
+
"grad_norm": 2.5370900630950928,
|
896 |
+
"learning_rate": 0.0001969726307942592,
|
897 |
+
"loss": 2.1515,
|
898 |
+
"step": 127
|
899 |
+
},
|
900 |
+
{
|
901 |
+
"epoch": 0.07735015296294898,
|
902 |
+
"grad_norm": 2.7379939556121826,
|
903 |
+
"learning_rate": 0.00019692092808720846,
|
904 |
+
"loss": 2.3117,
|
905 |
+
"step": 128
|
906 |
+
},
|
907 |
+
{
|
908 |
+
"epoch": 0.07795445103297201,
|
909 |
+
"grad_norm": 2.623459577560425,
|
910 |
+
"learning_rate": 0.0001968687945117896,
|
911 |
+
"loss": 2.2315,
|
912 |
+
"step": 129
|
913 |
+
},
|
914 |
+
{
|
915 |
+
"epoch": 0.07855874910299505,
|
916 |
+
"grad_norm": 2.609384775161743,
|
917 |
+
"learning_rate": 0.00019681623029976588,
|
918 |
+
"loss": 2.2411,
|
919 |
+
"step": 130
|
920 |
+
},
|
921 |
+
{
|
922 |
+
"epoch": 0.07916304717301809,
|
923 |
+
"grad_norm": 2.484173059463501,
|
924 |
+
"learning_rate": 0.00019676323568481498,
|
925 |
+
"loss": 2.0752,
|
926 |
+
"step": 131
|
927 |
+
},
|
928 |
+
{
|
929 |
+
"epoch": 0.07976734524304113,
|
930 |
+
"grad_norm": 2.5462472438812256,
|
931 |
+
"learning_rate": 0.00019670981090252792,
|
932 |
+
"loss": 2.2665,
|
933 |
+
"step": 132
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 0.08037164331306416,
|
937 |
+
"grad_norm": 2.5074727535247803,
|
938 |
+
"learning_rate": 0.00019665595619040808,
|
939 |
+
"loss": 2.2347,
|
940 |
+
"step": 133
|
941 |
+
},
|
942 |
+
{
|
943 |
+
"epoch": 0.08097594138308721,
|
944 |
+
"grad_norm": 2.9072914123535156,
|
945 |
+
"learning_rate": 0.0001966016717878702,
|
946 |
+
"loss": 2.2369,
|
947 |
+
"step": 134
|
948 |
+
},
|
949 |
+
{
|
950 |
+
"epoch": 0.08158023945311024,
|
951 |
+
"grad_norm": 2.8787453174591064,
|
952 |
+
"learning_rate": 0.00019654695793623907,
|
953 |
+
"loss": 2.2034,
|
954 |
+
"step": 135
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"epoch": 0.08218453752313329,
|
958 |
+
"grad_norm": 2.8111212253570557,
|
959 |
+
"learning_rate": 0.0001964918148787488,
|
960 |
+
"loss": 2.2064,
|
961 |
+
"step": 136
|
962 |
+
},
|
963 |
+
{
|
964 |
+
"epoch": 0.08278883559315632,
|
965 |
+
"grad_norm": 2.9196033477783203,
|
966 |
+
"learning_rate": 0.00019643624286054144,
|
967 |
+
"loss": 2.3142,
|
968 |
+
"step": 137
|
969 |
+
},
|
970 |
+
{
|
971 |
+
"epoch": 0.08339313366317937,
|
972 |
+
"grad_norm": 3.3923306465148926,
|
973 |
+
"learning_rate": 0.00019638024212866606,
|
974 |
+
"loss": 2.3254,
|
975 |
+
"step": 138
|
976 |
+
},
|
977 |
+
{
|
978 |
+
"epoch": 0.0839974317332024,
|
979 |
+
"grad_norm": 3.270350217819214,
|
980 |
+
"learning_rate": 0.0001963238129320776,
|
981 |
+
"loss": 2.3072,
|
982 |
+
"step": 139
|
983 |
+
},
|
984 |
+
{
|
985 |
+
"epoch": 0.08460172980322545,
|
986 |
+
"grad_norm": 3.227761745452881,
|
987 |
+
"learning_rate": 0.00019626695552163578,
|
988 |
+
"loss": 2.441,
|
989 |
+
"step": 140
|
990 |
+
},
|
991 |
+
{
|
992 |
+
"epoch": 0.08520602787324848,
|
993 |
+
"grad_norm": 3.1120471954345703,
|
994 |
+
"learning_rate": 0.00019620967015010395,
|
995 |
+
"loss": 2.5266,
|
996 |
+
"step": 141
|
997 |
+
},
|
998 |
+
{
|
999 |
+
"epoch": 0.08581032594327152,
|
1000 |
+
"grad_norm": 3.56309175491333,
|
1001 |
+
"learning_rate": 0.00019615195707214803,
|
1002 |
+
"loss": 2.1229,
|
1003 |
+
"step": 142
|
1004 |
+
},
|
1005 |
+
{
|
1006 |
+
"epoch": 0.08641462401329456,
|
1007 |
+
"grad_norm": 3.308427333831787,
|
1008 |
+
"learning_rate": 0.0001960938165443353,
|
1009 |
+
"loss": 2.3412,
|
1010 |
+
"step": 143
|
1011 |
+
},
|
1012 |
+
{
|
1013 |
+
"epoch": 0.0870189220833176,
|
1014 |
+
"grad_norm": 4.139370441436768,
|
1015 |
+
"learning_rate": 0.00019603524882513327,
|
1016 |
+
"loss": 2.6715,
|
1017 |
+
"step": 144
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 0.08762322015334063,
|
1021 |
+
"grad_norm": 4.013917922973633,
|
1022 |
+
"learning_rate": 0.0001959762541749086,
|
1023 |
+
"loss": 2.462,
|
1024 |
+
"step": 145
|
1025 |
+
},
|
1026 |
+
{
|
1027 |
+
"epoch": 0.08822751822336368,
|
1028 |
+
"grad_norm": 4.387619495391846,
|
1029 |
+
"learning_rate": 0.00019591683285592593,
|
1030 |
+
"loss": 2.7622,
|
1031 |
+
"step": 146
|
1032 |
+
},
|
1033 |
+
{
|
1034 |
+
"epoch": 0.08883181629338671,
|
1035 |
+
"grad_norm": 4.593787670135498,
|
1036 |
+
"learning_rate": 0.00019585698513234663,
|
1037 |
+
"loss": 2.8924,
|
1038 |
+
"step": 147
|
1039 |
+
},
|
1040 |
+
{
|
1041 |
+
"epoch": 0.08943611436340976,
|
1042 |
+
"grad_norm": 5.254031181335449,
|
1043 |
+
"learning_rate": 0.0001957967112702277,
|
1044 |
+
"loss": 2.8513,
|
1045 |
+
"step": 148
|
1046 |
+
},
|
1047 |
+
{
|
1048 |
+
"epoch": 0.09004041243343279,
|
1049 |
+
"grad_norm": 9.610785484313965,
|
1050 |
+
"learning_rate": 0.00019573601153752052,
|
1051 |
+
"loss": 3.7939,
|
1052 |
+
"step": 149
|
1053 |
+
},
|
1054 |
+
{
|
1055 |
+
"epoch": 0.09064471050345584,
|
1056 |
+
"grad_norm": 18.917434692382812,
|
1057 |
+
"learning_rate": 0.00019567488620406983,
|
1058 |
+
"loss": 4.2185,
|
1059 |
+
"step": 150
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 0.09124900857347887,
|
1063 |
+
"grad_norm": 2.803217649459839,
|
1064 |
+
"learning_rate": 0.00019561333554161224,
|
1065 |
+
"loss": 0.6506,
|
1066 |
+
"step": 151
|
1067 |
+
},
|
1068 |
+
{
|
1069 |
+
"epoch": 0.09185330664350191,
|
1070 |
+
"grad_norm": 2.6787402629852295,
|
1071 |
+
"learning_rate": 0.0001955513598237753,
|
1072 |
+
"loss": 1.4542,
|
1073 |
+
"step": 152
|
1074 |
+
},
|
1075 |
+
{
|
1076 |
+
"epoch": 0.09245760471352495,
|
1077 |
+
"grad_norm": 2.889517307281494,
|
1078 |
+
"learning_rate": 0.00019548895932607621,
|
1079 |
+
"loss": 1.9922,
|
1080 |
+
"step": 153
|
1081 |
+
},
|
1082 |
+
{
|
1083 |
+
"epoch": 0.09306190278354798,
|
1084 |
+
"grad_norm": 2.9428203105926514,
|
1085 |
+
"learning_rate": 0.00019542613432592038,
|
1086 |
+
"loss": 2.1081,
|
1087 |
+
"step": 154
|
1088 |
+
},
|
1089 |
+
{
|
1090 |
+
"epoch": 0.09366620085357102,
|
1091 |
+
"grad_norm": 2.6233069896698,
|
1092 |
+
"learning_rate": 0.00019536288510260056,
|
1093 |
+
"loss": 2.1672,
|
1094 |
+
"step": 155
|
1095 |
+
},
|
1096 |
+
{
|
1097 |
+
"epoch": 0.09427049892359406,
|
1098 |
+
"grad_norm": 2.8075478076934814,
|
1099 |
+
"learning_rate": 0.00019529921193729534,
|
1100 |
+
"loss": 2.2364,
|
1101 |
+
"step": 156
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 0.0948747969936171,
|
1105 |
+
"grad_norm": 2.7134907245635986,
|
1106 |
+
"learning_rate": 0.00019523511511306793,
|
1107 |
+
"loss": 2.2153,
|
1108 |
+
"step": 157
|
1109 |
+
},
|
1110 |
+
{
|
1111 |
+
"epoch": 0.09547909506364013,
|
1112 |
+
"grad_norm": 2.70220947265625,
|
1113 |
+
"learning_rate": 0.000195170594914865,
|
1114 |
+
"loss": 2.3958,
|
1115 |
+
"step": 158
|
1116 |
+
},
|
1117 |
+
{
|
1118 |
+
"epoch": 0.09608339313366318,
|
1119 |
+
"grad_norm": 2.827350378036499,
|
1120 |
+
"learning_rate": 0.00019510565162951537,
|
1121 |
+
"loss": 2.4202,
|
1122 |
+
"step": 159
|
1123 |
+
},
|
1124 |
+
{
|
1125 |
+
"epoch": 0.09668769120368621,
|
1126 |
+
"grad_norm": 2.6900534629821777,
|
1127 |
+
"learning_rate": 0.00019504028554572864,
|
1128 |
+
"loss": 2.3942,
|
1129 |
+
"step": 160
|
1130 |
+
},
|
1131 |
+
{
|
1132 |
+
"epoch": 0.09729198927370926,
|
1133 |
+
"grad_norm": 2.4423742294311523,
|
1134 |
+
"learning_rate": 0.00019497449695409408,
|
1135 |
+
"loss": 2.2381,
|
1136 |
+
"step": 161
|
1137 |
+
},
|
1138 |
+
{
|
1139 |
+
"epoch": 0.09789628734373229,
|
1140 |
+
"grad_norm": 2.530571222305298,
|
1141 |
+
"learning_rate": 0.00019490828614707916,
|
1142 |
+
"loss": 2.2482,
|
1143 |
+
"step": 162
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 0.09850058541375534,
|
1147 |
+
"grad_norm": 2.624455451965332,
|
1148 |
+
"learning_rate": 0.00019484165341902845,
|
1149 |
+
"loss": 2.1451,
|
1150 |
+
"step": 163
|
1151 |
+
},
|
1152 |
+
{
|
1153 |
+
"epoch": 0.09910488348377837,
|
1154 |
+
"grad_norm": 2.657663583755493,
|
1155 |
+
"learning_rate": 0.00019477459906616206,
|
1156 |
+
"loss": 1.9959,
|
1157 |
+
"step": 164
|
1158 |
+
},
|
1159 |
+
{
|
1160 |
+
"epoch": 0.09970918155380142,
|
1161 |
+
"grad_norm": 2.7544350624084473,
|
1162 |
+
"learning_rate": 0.00019470712338657458,
|
1163 |
+
"loss": 1.8559,
|
1164 |
+
"step": 165
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 0.10031347962382445,
|
1168 |
+
"grad_norm": 2.9291069507598877,
|
1169 |
+
"learning_rate": 0.0001946392266802336,
|
1170 |
+
"loss": 1.8975,
|
1171 |
+
"step": 166
|
1172 |
+
},
|
1173 |
+
{
|
1174 |
+
"epoch": 0.1009177776938475,
|
1175 |
+
"grad_norm": 2.9229235649108887,
|
1176 |
+
"learning_rate": 0.0001945709092489783,
|
1177 |
+
"loss": 1.992,
|
1178 |
+
"step": 167
|
1179 |
+
},
|
1180 |
+
{
|
1181 |
+
"epoch": 0.10152207576387053,
|
1182 |
+
"grad_norm": 2.5758590698242188,
|
1183 |
+
"learning_rate": 0.00019450217139651844,
|
1184 |
+
"loss": 1.8534,
|
1185 |
+
"step": 168
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 0.10212637383389357,
|
1189 |
+
"grad_norm": 2.4789786338806152,
|
1190 |
+
"learning_rate": 0.0001944330134284326,
|
1191 |
+
"loss": 2.0086,
|
1192 |
+
"step": 169
|
1193 |
+
},
|
1194 |
+
{
|
1195 |
+
"epoch": 0.1027306719039166,
|
1196 |
+
"grad_norm": 2.6959614753723145,
|
1197 |
+
"learning_rate": 0.00019436343565216711,
|
1198 |
+
"loss": 2.0508,
|
1199 |
+
"step": 170
|
1200 |
+
},
|
1201 |
+
{
|
1202 |
+
"epoch": 0.10333496997393965,
|
1203 |
+
"grad_norm": 2.539034128189087,
|
1204 |
+
"learning_rate": 0.00019429343837703455,
|
1205 |
+
"loss": 2.0941,
|
1206 |
+
"step": 171
|
1207 |
+
},
|
1208 |
+
{
|
1209 |
+
"epoch": 0.10393926804396268,
|
1210 |
+
"grad_norm": 2.679861068725586,
|
1211 |
+
"learning_rate": 0.0001942230219142124,
|
1212 |
+
"loss": 1.9783,
|
1213 |
+
"step": 172
|
1214 |
+
},
|
1215 |
+
{
|
1216 |
+
"epoch": 0.10454356611398573,
|
1217 |
+
"grad_norm": 2.8474485874176025,
|
1218 |
+
"learning_rate": 0.0001941521865767417,
|
1219 |
+
"loss": 1.9477,
|
1220 |
+
"step": 173
|
1221 |
+
},
|
1222 |
+
{
|
1223 |
+
"epoch": 0.10514786418400876,
|
1224 |
+
"grad_norm": 2.6970903873443604,
|
1225 |
+
"learning_rate": 0.0001940809326795256,
|
1226 |
+
"loss": 1.9986,
|
1227 |
+
"step": 174
|
1228 |
+
},
|
1229 |
+
{
|
1230 |
+
"epoch": 0.1057521622540318,
|
1231 |
+
"grad_norm": 2.604323387145996,
|
1232 |
+
"learning_rate": 0.000194009260539328,
|
1233 |
+
"loss": 2.15,
|
1234 |
+
"step": 175
|
1235 |
+
},
|
1236 |
+
{
|
1237 |
+
"epoch": 0.10635646032405484,
|
1238 |
+
"grad_norm": 3.2425715923309326,
|
1239 |
+
"learning_rate": 0.0001939371704747721,
|
1240 |
+
"loss": 2.1733,
|
1241 |
+
"step": 176
|
1242 |
+
},
|
1243 |
+
{
|
1244 |
+
"epoch": 0.10696075839407788,
|
1245 |
+
"grad_norm": 2.805544853210449,
|
1246 |
+
"learning_rate": 0.00019386466280633906,
|
1247 |
+
"loss": 2.1526,
|
1248 |
+
"step": 177
|
1249 |
+
},
|
1250 |
+
{
|
1251 |
+
"epoch": 0.10756505646410092,
|
1252 |
+
"grad_norm": 2.6435155868530273,
|
1253 |
+
"learning_rate": 0.00019379173785636646,
|
1254 |
+
"loss": 2.2713,
|
1255 |
+
"step": 178
|
1256 |
+
},
|
1257 |
+
{
|
1258 |
+
"epoch": 0.10816935453412396,
|
1259 |
+
"grad_norm": 3.0403223037719727,
|
1260 |
+
"learning_rate": 0.000193718395949047,
|
1261 |
+
"loss": 2.171,
|
1262 |
+
"step": 179
|
1263 |
+
},
|
1264 |
+
{
|
1265 |
+
"epoch": 0.108773652604147,
|
1266 |
+
"grad_norm": 2.9794914722442627,
|
1267 |
+
"learning_rate": 0.00019364463741042694,
|
1268 |
+
"loss": 2.1918,
|
1269 |
+
"step": 180
|
1270 |
+
},
|
1271 |
+
{
|
1272 |
+
"epoch": 0.10937795067417004,
|
1273 |
+
"grad_norm": 3.198793411254883,
|
1274 |
+
"learning_rate": 0.00019357046256840473,
|
1275 |
+
"loss": 2.3307,
|
1276 |
+
"step": 181
|
1277 |
+
},
|
1278 |
+
{
|
1279 |
+
"epoch": 0.10998224874419307,
|
1280 |
+
"grad_norm": 3.435657262802124,
|
1281 |
+
"learning_rate": 0.00019349587175272948,
|
1282 |
+
"loss": 1.9757,
|
1283 |
+
"step": 182
|
1284 |
+
},
|
1285 |
+
{
|
1286 |
+
"epoch": 0.11058654681421612,
|
1287 |
+
"grad_norm": 3.1969451904296875,
|
1288 |
+
"learning_rate": 0.0001934208652949996,
|
1289 |
+
"loss": 2.2,
|
1290 |
+
"step": 183
|
1291 |
+
},
|
1292 |
+
{
|
1293 |
+
"epoch": 0.11119084488423915,
|
1294 |
+
"grad_norm": 3.012925863265991,
|
1295 |
+
"learning_rate": 0.00019334544352866127,
|
1296 |
+
"loss": 2.1743,
|
1297 |
+
"step": 184
|
1298 |
+
},
|
1299 |
+
{
|
1300 |
+
"epoch": 0.11179514295426218,
|
1301 |
+
"grad_norm": 3.455808162689209,
|
1302 |
+
"learning_rate": 0.00019326960678900688,
|
1303 |
+
"loss": 2.0939,
|
1304 |
+
"step": 185
|
1305 |
+
},
|
1306 |
+
{
|
1307 |
+
"epoch": 0.11239944102428523,
|
1308 |
+
"grad_norm": 3.4885973930358887,
|
1309 |
+
"learning_rate": 0.00019319335541317361,
|
1310 |
+
"loss": 2.0869,
|
1311 |
+
"step": 186
|
1312 |
+
},
|
1313 |
+
{
|
1314 |
+
"epoch": 0.11300373909430826,
|
1315 |
+
"grad_norm": 3.6527769565582275,
|
1316 |
+
"learning_rate": 0.00019311668974014208,
|
1317 |
+
"loss": 2.1132,
|
1318 |
+
"step": 187
|
1319 |
+
},
|
1320 |
+
{
|
1321 |
+
"epoch": 0.11360803716433131,
|
1322 |
+
"grad_norm": 3.5603349208831787,
|
1323 |
+
"learning_rate": 0.00019303961011073447,
|
1324 |
+
"loss": 2.495,
|
1325 |
+
"step": 188
|
1326 |
+
},
|
1327 |
+
{
|
1328 |
+
"epoch": 0.11421233523435434,
|
1329 |
+
"grad_norm": 4.438934326171875,
|
1330 |
+
"learning_rate": 0.00019296211686761346,
|
1331 |
+
"loss": 2.2977,
|
1332 |
+
"step": 189
|
1333 |
+
},
|
1334 |
+
{
|
1335 |
+
"epoch": 0.11481663330437739,
|
1336 |
+
"grad_norm": 3.6968555450439453,
|
1337 |
+
"learning_rate": 0.00019288421035528028,
|
1338 |
+
"loss": 2.2683,
|
1339 |
+
"step": 190
|
1340 |
+
},
|
1341 |
+
{
|
1342 |
+
"epoch": 0.11542093137440042,
|
1343 |
+
"grad_norm": 4.076991081237793,
|
1344 |
+
"learning_rate": 0.00019280589092007352,
|
1345 |
+
"loss": 2.5081,
|
1346 |
+
"step": 191
|
1347 |
+
},
|
1348 |
+
{
|
1349 |
+
"epoch": 0.11602522944442346,
|
1350 |
+
"grad_norm": 3.8638432025909424,
|
1351 |
+
"learning_rate": 0.00019272715891016735,
|
1352 |
+
"loss": 2.3628,
|
1353 |
+
"step": 192
|
1354 |
+
},
|
1355 |
+
{
|
1356 |
+
"epoch": 0.1166295275144465,
|
1357 |
+
"grad_norm": 3.8374760150909424,
|
1358 |
+
"learning_rate": 0.00019264801467557007,
|
1359 |
+
"loss": 2.1119,
|
1360 |
+
"step": 193
|
1361 |
+
},
|
1362 |
+
{
|
1363 |
+
"epoch": 0.11723382558446954,
|
1364 |
+
"grad_norm": 3.7434163093566895,
|
1365 |
+
"learning_rate": 0.00019256845856812266,
|
1366 |
+
"loss": 2.1354,
|
1367 |
+
"step": 194
|
1368 |
+
},
|
1369 |
+
{
|
1370 |
+
"epoch": 0.11783812365449257,
|
1371 |
+
"grad_norm": 5.35501766204834,
|
1372 |
+
"learning_rate": 0.000192488490941497,
|
1373 |
+
"loss": 2.5971,
|
1374 |
+
"step": 195
|
1375 |
+
},
|
1376 |
+
{
|
1377 |
+
"epoch": 0.11844242172451562,
|
1378 |
+
"grad_norm": 5.991562843322754,
|
1379 |
+
"learning_rate": 0.00019240811215119448,
|
1380 |
+
"loss": 2.8775,
|
1381 |
+
"step": 196
|
1382 |
+
},
|
1383 |
+
{
|
1384 |
+
"epoch": 0.11904671979453865,
|
1385 |
+
"grad_norm": 5.207497596740723,
|
1386 |
+
"learning_rate": 0.00019232732255454422,
|
1387 |
+
"loss": 2.7139,
|
1388 |
+
"step": 197
|
1389 |
+
},
|
1390 |
+
{
|
1391 |
+
"epoch": 0.1196510178645617,
|
1392 |
+
"grad_norm": 6.914007663726807,
|
1393 |
+
"learning_rate": 0.00019224612251070175,
|
1394 |
+
"loss": 2.8393,
|
1395 |
+
"step": 198
|
1396 |
+
},
|
1397 |
+
{
|
1398 |
+
"epoch": 0.12025531593458473,
|
1399 |
+
"grad_norm": 14.335077285766602,
|
1400 |
+
"learning_rate": 0.0001921645123806472,
|
1401 |
+
"loss": 3.909,
|
1402 |
+
"step": 199
|
1403 |
+
},
|
1404 |
+
{
|
1405 |
+
"epoch": 0.12085961400460778,
|
1406 |
+
"grad_norm": 22.205036163330078,
|
1407 |
+
"learning_rate": 0.0001920824925271838,
|
1408 |
+
"loss": 3.9603,
|
1409 |
+
"step": 200
|
1410 |
+
},
|
1411 |
+
{
|
1412 |
+
"epoch": 0.12146391207463081,
|
1413 |
+
"grad_norm": 2.610422134399414,
|
1414 |
+
"learning_rate": 0.0001920000633149362,
|
1415 |
+
"loss": 0.6103,
|
1416 |
+
"step": 201
|
1417 |
+
},
|
1418 |
+
{
|
1419 |
+
"epoch": 0.12206821014465385,
|
1420 |
+
"grad_norm": 2.129725217819214,
|
1421 |
+
"learning_rate": 0.00019191722511034884,
|
1422 |
+
"loss": 0.9237,
|
1423 |
+
"step": 202
|
1424 |
+
},
|
1425 |
+
{
|
1426 |
+
"epoch": 0.12267250821467689,
|
1427 |
+
"grad_norm": 2.469688892364502,
|
1428 |
+
"learning_rate": 0.00019183397828168448,
|
1429 |
+
"loss": 1.882,
|
1430 |
+
"step": 203
|
1431 |
+
},
|
1432 |
+
{
|
1433 |
+
"epoch": 0.12327680628469993,
|
1434 |
+
"grad_norm": 2.8455584049224854,
|
1435 |
+
"learning_rate": 0.00019175032319902234,
|
1436 |
+
"loss": 2.0722,
|
1437 |
+
"step": 204
|
1438 |
+
},
|
1439 |
+
{
|
1440 |
+
"epoch": 0.12388110435472297,
|
1441 |
+
"grad_norm": 2.6948962211608887,
|
1442 |
+
"learning_rate": 0.00019166626023425662,
|
1443 |
+
"loss": 2.0877,
|
1444 |
+
"step": 205
|
1445 |
+
},
|
1446 |
+
{
|
1447 |
+
"epoch": 0.12448540242474601,
|
1448 |
+
"grad_norm": 2.7360682487487793,
|
1449 |
+
"learning_rate": 0.00019158178976109476,
|
1450 |
+
"loss": 2.2041,
|
1451 |
+
"step": 206
|
1452 |
+
},
|
1453 |
+
{
|
1454 |
+
"epoch": 0.12508970049476906,
|
1455 |
+
"grad_norm": 2.775461435317993,
|
1456 |
+
"learning_rate": 0.0001914969121550558,
|
1457 |
+
"loss": 2.2209,
|
1458 |
+
"step": 207
|
1459 |
+
},
|
1460 |
+
{
|
1461 |
+
"epoch": 0.12569399856479208,
|
1462 |
+
"grad_norm": 2.772085428237915,
|
1463 |
+
"learning_rate": 0.00019141162779346874,
|
1464 |
+
"loss": 2.3135,
|
1465 |
+
"step": 208
|
1466 |
+
},
|
1467 |
+
{
|
1468 |
+
"epoch": 0.12629829663481512,
|
1469 |
+
"grad_norm": 2.701401710510254,
|
1470 |
+
"learning_rate": 0.00019132593705547082,
|
1471 |
+
"loss": 2.354,
|
1472 |
+
"step": 209
|
1473 |
+
},
|
1474 |
+
{
|
1475 |
+
"epoch": 0.12690259470483817,
|
1476 |
+
"grad_norm": 2.7918756008148193,
|
1477 |
+
"learning_rate": 0.00019123984032200586,
|
1478 |
+
"loss": 2.3682,
|
1479 |
+
"step": 210
|
1480 |
+
},
|
1481 |
+
{
|
1482 |
+
"epoch": 0.1275068927748612,
|
1483 |
+
"grad_norm": 2.71183705329895,
|
1484 |
+
"learning_rate": 0.00019115333797582254,
|
1485 |
+
"loss": 2.3986,
|
1486 |
+
"step": 211
|
1487 |
+
},
|
1488 |
+
{
|
1489 |
+
"epoch": 0.12811119084488423,
|
1490 |
+
"grad_norm": 2.859503984451294,
|
1491 |
+
"learning_rate": 0.00019106643040147278,
|
1492 |
+
"loss": 2.2909,
|
1493 |
+
"step": 212
|
1494 |
+
},
|
1495 |
+
{
|
1496 |
+
"epoch": 0.12871548891490728,
|
1497 |
+
"grad_norm": 2.7157833576202393,
|
1498 |
+
"learning_rate": 0.00019097911798530987,
|
1499 |
+
"loss": 1.9269,
|
1500 |
+
"step": 213
|
1501 |
+
},
|
1502 |
+
{
|
1503 |
+
"epoch": 0.12931978698493032,
|
1504 |
+
"grad_norm": 2.9616880416870117,
|
1505 |
+
"learning_rate": 0.00019089140111548696,
|
1506 |
+
"loss": 2.0798,
|
1507 |
+
"step": 214
|
1508 |
+
},
|
1509 |
+
{
|
1510 |
+
"epoch": 0.12992408505495334,
|
1511 |
+
"grad_norm": 2.9561362266540527,
|
1512 |
+
"learning_rate": 0.00019080328018195513,
|
1513 |
+
"loss": 2.0269,
|
1514 |
+
"step": 215
|
1515 |
+
},
|
1516 |
+
{
|
1517 |
+
"epoch": 0.1305283831249764,
|
1518 |
+
"grad_norm": 2.5822503566741943,
|
1519 |
+
"learning_rate": 0.0001907147555764618,
|
1520 |
+
"loss": 1.8083,
|
1521 |
+
"step": 216
|
1522 |
+
},
|
1523 |
+
{
|
1524 |
+
"epoch": 0.13113268119499943,
|
1525 |
+
"grad_norm": 2.9241294860839844,
|
1526 |
+
"learning_rate": 0.00019062582769254895,
|
1527 |
+
"loss": 2.0313,
|
1528 |
+
"step": 217
|
1529 |
+
},
|
1530 |
+
{
|
1531 |
+
"epoch": 0.13173697926502248,
|
1532 |
+
"grad_norm": 3.371105432510376,
|
1533 |
+
"learning_rate": 0.00019053649692555135,
|
1534 |
+
"loss": 1.8889,
|
1535 |
+
"step": 218
|
1536 |
+
},
|
1537 |
+
{
|
1538 |
+
"epoch": 0.1323412773350455,
|
1539 |
+
"grad_norm": 2.92676043510437,
|
1540 |
+
"learning_rate": 0.00019044676367259476,
|
1541 |
+
"loss": 2.1494,
|
1542 |
+
"step": 219
|
1543 |
+
},
|
1544 |
+
{
|
1545 |
+
"epoch": 0.13294557540506854,
|
1546 |
+
"grad_norm": 2.9326910972595215,
|
1547 |
+
"learning_rate": 0.00019035662833259432,
|
1548 |
+
"loss": 1.8016,
|
1549 |
+
"step": 220
|
1550 |
+
},
|
1551 |
+
{
|
1552 |
+
"epoch": 0.1335498734750916,
|
1553 |
+
"grad_norm": 2.7013325691223145,
|
1554 |
+
"learning_rate": 0.00019026609130625257,
|
1555 |
+
"loss": 1.9979,
|
1556 |
+
"step": 221
|
1557 |
+
},
|
1558 |
+
{
|
1559 |
+
"epoch": 0.13415417154511464,
|
1560 |
+
"grad_norm": 2.9696829319000244,
|
1561 |
+
"learning_rate": 0.00019017515299605788,
|
1562 |
+
"loss": 2.0573,
|
1563 |
+
"step": 222
|
1564 |
+
},
|
1565 |
+
{
|
1566 |
+
"epoch": 0.13475846961513765,
|
1567 |
+
"grad_norm": 3.2566845417022705,
|
1568 |
+
"learning_rate": 0.00019008381380628247,
|
1569 |
+
"loss": 2.0659,
|
1570 |
+
"step": 223
|
1571 |
+
},
|
1572 |
+
{
|
1573 |
+
"epoch": 0.1353627676851607,
|
1574 |
+
"grad_norm": 3.4677469730377197,
|
1575 |
+
"learning_rate": 0.00018999207414298067,
|
1576 |
+
"loss": 2.123,
|
1577 |
+
"step": 224
|
1578 |
+
},
|
1579 |
+
{
|
1580 |
+
"epoch": 0.13596706575518375,
|
1581 |
+
"grad_norm": 2.9905354976654053,
|
1582 |
+
"learning_rate": 0.00018989993441398726,
|
1583 |
+
"loss": 2.1558,
|
1584 |
+
"step": 225
|
1585 |
+
},
|
1586 |
+
{
|
1587 |
+
"epoch": 0.1365713638252068,
|
1588 |
+
"grad_norm": 3.78269362449646,
|
1589 |
+
"learning_rate": 0.00018980739502891546,
|
1590 |
+
"loss": 2.2024,
|
1591 |
+
"step": 226
|
1592 |
+
},
|
1593 |
+
{
|
1594 |
+
"epoch": 0.1371756618952298,
|
1595 |
+
"grad_norm": 3.0096099376678467,
|
1596 |
+
"learning_rate": 0.0001897144563991552,
|
1597 |
+
"loss": 2.0295,
|
1598 |
+
"step": 227
|
1599 |
+
},
|
1600 |
+
{
|
1601 |
+
"epoch": 0.13777995996525286,
|
1602 |
+
"grad_norm": 2.9910919666290283,
|
1603 |
+
"learning_rate": 0.00018962111893787128,
|
1604 |
+
"loss": 2.0755,
|
1605 |
+
"step": 228
|
1606 |
+
},
|
1607 |
+
{
|
1608 |
+
"epoch": 0.1383842580352759,
|
1609 |
+
"grad_norm": 3.3000521659851074,
|
1610 |
+
"learning_rate": 0.00018952738306000151,
|
1611 |
+
"loss": 2.1896,
|
1612 |
+
"step": 229
|
1613 |
+
},
|
1614 |
+
{
|
1615 |
+
"epoch": 0.13898855610529895,
|
1616 |
+
"grad_norm": 3.4028759002685547,
|
1617 |
+
"learning_rate": 0.00018943324918225494,
|
1618 |
+
"loss": 2.1814,
|
1619 |
+
"step": 230
|
1620 |
+
},
|
1621 |
+
{
|
1622 |
+
"epoch": 0.13959285417532197,
|
1623 |
+
"grad_norm": 3.4083681106567383,
|
1624 |
+
"learning_rate": 0.0001893387177231099,
|
1625 |
+
"loss": 2.1202,
|
1626 |
+
"step": 231
|
1627 |
+
},
|
1628 |
+
{
|
1629 |
+
"epoch": 0.140197152245345,
|
1630 |
+
"grad_norm": 3.344849109649658,
|
1631 |
+
"learning_rate": 0.0001892437891028122,
|
1632 |
+
"loss": 2.2417,
|
1633 |
+
"step": 232
|
1634 |
+
},
|
1635 |
+
{
|
1636 |
+
"epoch": 0.14080145031536806,
|
1637 |
+
"grad_norm": 3.3460681438446045,
|
1638 |
+
"learning_rate": 0.0001891484637433733,
|
1639 |
+
"loss": 2.2566,
|
1640 |
+
"step": 233
|
1641 |
+
},
|
1642 |
+
{
|
1643 |
+
"epoch": 0.1414057483853911,
|
1644 |
+
"grad_norm": 3.230792284011841,
|
1645 |
+
"learning_rate": 0.00018905274206856837,
|
1646 |
+
"loss": 2.1327,
|
1647 |
+
"step": 234
|
1648 |
+
},
|
1649 |
+
{
|
1650 |
+
"epoch": 0.14201004645541412,
|
1651 |
+
"grad_norm": 3.6352362632751465,
|
1652 |
+
"learning_rate": 0.00018895662450393438,
|
1653 |
+
"loss": 2.2026,
|
1654 |
+
"step": 235
|
1655 |
+
},
|
1656 |
+
{
|
1657 |
+
"epoch": 0.14261434452543717,
|
1658 |
+
"grad_norm": 3.4648375511169434,
|
1659 |
+
"learning_rate": 0.00018886011147676833,
|
1660 |
+
"loss": 2.2437,
|
1661 |
+
"step": 236
|
1662 |
+
},
|
1663 |
+
{
|
1664 |
+
"epoch": 0.14321864259546022,
|
1665 |
+
"grad_norm": 3.5209550857543945,
|
1666 |
+
"learning_rate": 0.00018876320341612522,
|
1667 |
+
"loss": 2.3193,
|
1668 |
+
"step": 237
|
1669 |
+
},
|
1670 |
+
{
|
1671 |
+
"epoch": 0.14382294066548326,
|
1672 |
+
"grad_norm": 3.629462242126465,
|
1673 |
+
"learning_rate": 0.00018866590075281624,
|
1674 |
+
"loss": 2.2131,
|
1675 |
+
"step": 238
|
1676 |
+
},
|
1677 |
+
{
|
1678 |
+
"epoch": 0.14442723873550628,
|
1679 |
+
"grad_norm": 3.810232400894165,
|
1680 |
+
"learning_rate": 0.00018856820391940674,
|
1681 |
+
"loss": 2.2062,
|
1682 |
+
"step": 239
|
1683 |
+
},
|
1684 |
+
{
|
1685 |
+
"epoch": 0.14503153680552933,
|
1686 |
+
"grad_norm": 4.461780071258545,
|
1687 |
+
"learning_rate": 0.00018847011335021449,
|
1688 |
+
"loss": 2.336,
|
1689 |
+
"step": 240
|
1690 |
+
},
|
1691 |
+
{
|
1692 |
+
"epoch": 0.14563583487555237,
|
1693 |
+
"grad_norm": 3.840716600418091,
|
1694 |
+
"learning_rate": 0.00018837162948130752,
|
1695 |
+
"loss": 2.1435,
|
1696 |
+
"step": 241
|
1697 |
+
},
|
1698 |
+
{
|
1699 |
+
"epoch": 0.14624013294557542,
|
1700 |
+
"grad_norm": 4.086057186126709,
|
1701 |
+
"learning_rate": 0.00018827275275050233,
|
1702 |
+
"loss": 2.2668,
|
1703 |
+
"step": 242
|
1704 |
+
},
|
1705 |
+
{
|
1706 |
+
"epoch": 0.14684443101559844,
|
1707 |
+
"grad_norm": 4.305682182312012,
|
1708 |
+
"learning_rate": 0.00018817348359736203,
|
1709 |
+
"loss": 2.5264,
|
1710 |
+
"step": 243
|
1711 |
+
},
|
1712 |
+
{
|
1713 |
+
"epoch": 0.14744872908562148,
|
1714 |
+
"grad_norm": 4.541891098022461,
|
1715 |
+
"learning_rate": 0.00018807382246319412,
|
1716 |
+
"loss": 2.4166,
|
1717 |
+
"step": 244
|
1718 |
+
},
|
1719 |
+
{
|
1720 |
+
"epoch": 0.14805302715564453,
|
1721 |
+
"grad_norm": 4.768816947937012,
|
1722 |
+
"learning_rate": 0.00018797376979104872,
|
1723 |
+
"loss": 2.6156,
|
1724 |
+
"step": 245
|
1725 |
+
},
|
1726 |
+
{
|
1727 |
+
"epoch": 0.14865732522566755,
|
1728 |
+
"grad_norm": 6.231074333190918,
|
1729 |
+
"learning_rate": 0.00018787332602571662,
|
1730 |
+
"loss": 2.5208,
|
1731 |
+
"step": 246
|
1732 |
+
},
|
1733 |
+
{
|
1734 |
+
"epoch": 0.1492616232956906,
|
1735 |
+
"grad_norm": 6.638082504272461,
|
1736 |
+
"learning_rate": 0.00018777249161372713,
|
1737 |
+
"loss": 2.7291,
|
1738 |
+
"step": 247
|
1739 |
+
},
|
1740 |
+
{
|
1741 |
+
"epoch": 0.14986592136571364,
|
1742 |
+
"grad_norm": 7.254632472991943,
|
1743 |
+
"learning_rate": 0.00018767126700334634,
|
1744 |
+
"loss": 3.0853,
|
1745 |
+
"step": 248
|
1746 |
+
},
|
1747 |
+
{
|
1748 |
+
"epoch": 0.15047021943573669,
|
1749 |
+
"grad_norm": 15.801924705505371,
|
1750 |
+
"learning_rate": 0.0001875696526445749,
|
1751 |
+
"loss": 3.792,
|
1752 |
+
"step": 249
|
1753 |
+
},
|
1754 |
+
{
|
1755 |
+
"epoch": 0.1510745175057597,
|
1756 |
+
"grad_norm": 34.2322883605957,
|
1757 |
+
"learning_rate": 0.0001874676489891461,
|
1758 |
+
"loss": 4.3077,
|
1759 |
+
"step": 250
|
1760 |
+
},
|
1761 |
+
{
|
1762 |
+
"epoch": 0.15167881557578275,
|
1763 |
+
"grad_norm": 2.6348602771759033,
|
1764 |
+
"learning_rate": 0.00018736525649052394,
|
1765 |
+
"loss": 0.6426,
|
1766 |
+
"step": 251
|
1767 |
+
},
|
1768 |
+
{
|
1769 |
+
"epoch": 0.1522831136458058,
|
1770 |
+
"grad_norm": 2.4239795207977295,
|
1771 |
+
"learning_rate": 0.00018726247560390099,
|
1772 |
+
"loss": 1.3992,
|
1773 |
+
"step": 252
|
1774 |
+
},
|
1775 |
+
{
|
1776 |
+
"epoch": 0.15288741171582884,
|
1777 |
+
"grad_norm": 2.6609582901000977,
|
1778 |
+
"learning_rate": 0.00018715930678619644,
|
1779 |
+
"loss": 1.9515,
|
1780 |
+
"step": 253
|
1781 |
+
},
|
1782 |
+
{
|
1783 |
+
"epoch": 0.15349170978585186,
|
1784 |
+
"grad_norm": 2.8232662677764893,
|
1785 |
+
"learning_rate": 0.00018705575049605413,
|
1786 |
+
"loss": 2.2264,
|
1787 |
+
"step": 254
|
1788 |
+
},
|
1789 |
+
{
|
1790 |
+
"epoch": 0.1540960078558749,
|
1791 |
+
"grad_norm": 3.030365467071533,
|
1792 |
+
"learning_rate": 0.00018695180719384029,
|
1793 |
+
"loss": 2.1837,
|
1794 |
+
"step": 255
|
1795 |
+
},
|
1796 |
+
{
|
1797 |
+
"epoch": 0.15470030592589795,
|
1798 |
+
"grad_norm": 2.785435199737549,
|
1799 |
+
"learning_rate": 0.00018684747734164177,
|
1800 |
+
"loss": 2.1539,
|
1801 |
+
"step": 256
|
1802 |
+
},
|
1803 |
+
{
|
1804 |
+
"epoch": 0.155304603995921,
|
1805 |
+
"grad_norm": 2.9929676055908203,
|
1806 |
+
"learning_rate": 0.00018674276140326376,
|
1807 |
+
"loss": 2.2902,
|
1808 |
+
"step": 257
|
1809 |
+
},
|
1810 |
+
{
|
1811 |
+
"epoch": 0.15590890206594402,
|
1812 |
+
"grad_norm": 2.787749767303467,
|
1813 |
+
"learning_rate": 0.00018663765984422786,
|
1814 |
+
"loss": 2.2207,
|
1815 |
+
"step": 258
|
1816 |
+
},
|
1817 |
+
{
|
1818 |
+
"epoch": 0.15651320013596706,
|
1819 |
+
"grad_norm": 3.058166742324829,
|
1820 |
+
"learning_rate": 0.00018653217313177004,
|
1821 |
+
"loss": 2.328,
|
1822 |
+
"step": 259
|
1823 |
+
},
|
1824 |
+
{
|
1825 |
+
"epoch": 0.1571174982059901,
|
1826 |
+
"grad_norm": 2.885544776916504,
|
1827 |
+
"learning_rate": 0.00018642630173483832,
|
1828 |
+
"loss": 2.4258,
|
1829 |
+
"step": 260
|
1830 |
+
},
|
1831 |
+
{
|
1832 |
+
"epoch": 0.15772179627601315,
|
1833 |
+
"grad_norm": 2.925114870071411,
|
1834 |
+
"learning_rate": 0.00018632004612409103,
|
1835 |
+
"loss": 2.267,
|
1836 |
+
"step": 261
|
1837 |
+
},
|
1838 |
+
{
|
1839 |
+
"epoch": 0.15832609434603617,
|
1840 |
+
"grad_norm": 3.052964210510254,
|
1841 |
+
"learning_rate": 0.00018621340677189453,
|
1842 |
+
"loss": 2.1573,
|
1843 |
+
"step": 262
|
1844 |
+
},
|
1845 |
+
{
|
1846 |
+
"epoch": 0.15893039241605922,
|
1847 |
+
"grad_norm": 3.1201493740081787,
|
1848 |
+
"learning_rate": 0.00018610638415232097,
|
1849 |
+
"loss": 1.9854,
|
1850 |
+
"step": 263
|
1851 |
+
},
|
1852 |
+
{
|
1853 |
+
"epoch": 0.15953469048608226,
|
1854 |
+
"grad_norm": 3.032017946243286,
|
1855 |
+
"learning_rate": 0.00018599897874114652,
|
1856 |
+
"loss": 2.0349,
|
1857 |
+
"step": 264
|
1858 |
+
},
|
1859 |
+
{
|
1860 |
+
"epoch": 0.1601389885561053,
|
1861 |
+
"grad_norm": 2.9624085426330566,
|
1862 |
+
"learning_rate": 0.00018589119101584898,
|
1863 |
+
"loss": 1.8199,
|
1864 |
+
"step": 265
|
1865 |
+
},
|
1866 |
+
{
|
1867 |
+
"epoch": 0.16074328662612833,
|
1868 |
+
"grad_norm": 3.859501361846924,
|
1869 |
+
"learning_rate": 0.00018578302145560584,
|
1870 |
+
"loss": 1.8289,
|
1871 |
+
"step": 266
|
1872 |
+
},
|
1873 |
+
{
|
1874 |
+
"epoch": 0.16134758469615137,
|
1875 |
+
"grad_norm": 3.10041880607605,
|
1876 |
+
"learning_rate": 0.00018567447054129195,
|
1877 |
+
"loss": 1.8516,
|
1878 |
+
"step": 267
|
1879 |
+
},
|
1880 |
+
{
|
1881 |
+
"epoch": 0.16195188276617442,
|
1882 |
+
"grad_norm": 3.583569288253784,
|
1883 |
+
"learning_rate": 0.00018556553875547754,
|
1884 |
+
"loss": 1.9975,
|
1885 |
+
"step": 268
|
1886 |
+
},
|
1887 |
+
{
|
1888 |
+
"epoch": 0.16255618083619747,
|
1889 |
+
"grad_norm": 2.8302621841430664,
|
1890 |
+
"learning_rate": 0.00018545622658242607,
|
1891 |
+
"loss": 1.9481,
|
1892 |
+
"step": 269
|
1893 |
+
},
|
1894 |
+
{
|
1895 |
+
"epoch": 0.16316047890622049,
|
1896 |
+
"grad_norm": 2.866164207458496,
|
1897 |
+
"learning_rate": 0.00018534653450809197,
|
1898 |
+
"loss": 1.8458,
|
1899 |
+
"step": 270
|
1900 |
+
},
|
1901 |
+
{
|
1902 |
+
"epoch": 0.16376477697624353,
|
1903 |
+
"grad_norm": 2.974346399307251,
|
1904 |
+
"learning_rate": 0.00018523646302011867,
|
1905 |
+
"loss": 1.9694,
|
1906 |
+
"step": 271
|
1907 |
+
},
|
1908 |
+
{
|
1909 |
+
"epoch": 0.16436907504626658,
|
1910 |
+
"grad_norm": 3.0076396465301514,
|
1911 |
+
"learning_rate": 0.00018512601260783606,
|
1912 |
+
"loss": 2.0929,
|
1913 |
+
"step": 272
|
1914 |
+
},
|
1915 |
+
{
|
1916 |
+
"epoch": 0.16497337311628962,
|
1917 |
+
"grad_norm": 3.253673553466797,
|
1918 |
+
"learning_rate": 0.00018501518376225887,
|
1919 |
+
"loss": 2.0573,
|
1920 |
+
"step": 273
|
1921 |
+
},
|
1922 |
+
{
|
1923 |
+
"epoch": 0.16557767118631264,
|
1924 |
+
"grad_norm": 3.42087721824646,
|
1925 |
+
"learning_rate": 0.00018490397697608395,
|
1926 |
+
"loss": 2.0241,
|
1927 |
+
"step": 274
|
1928 |
+
},
|
1929 |
+
{
|
1930 |
+
"epoch": 0.1661819692563357,
|
1931 |
+
"grad_norm": 3.4087624549865723,
|
1932 |
+
"learning_rate": 0.0001847923927436884,
|
1933 |
+
"loss": 2.0986,
|
1934 |
+
"step": 275
|
1935 |
+
},
|
1936 |
+
{
|
1937 |
+
"epoch": 0.16678626732635873,
|
1938 |
+
"grad_norm": 3.0722851753234863,
|
1939 |
+
"learning_rate": 0.00018468043156112728,
|
1940 |
+
"loss": 2.1384,
|
1941 |
+
"step": 276
|
1942 |
+
},
|
1943 |
+
{
|
1944 |
+
"epoch": 0.16739056539638175,
|
1945 |
+
"grad_norm": 3.203979730606079,
|
1946 |
+
"learning_rate": 0.0001845680939261314,
|
1947 |
+
"loss": 2.2446,
|
1948 |
+
"step": 277
|
1949 |
+
},
|
1950 |
+
{
|
1951 |
+
"epoch": 0.1679948634664048,
|
1952 |
+
"grad_norm": 3.2715237140655518,
|
1953 |
+
"learning_rate": 0.00018445538033810515,
|
1954 |
+
"loss": 2.1088,
|
1955 |
+
"step": 278
|
1956 |
+
},
|
1957 |
+
{
|
1958 |
+
"epoch": 0.16859916153642784,
|
1959 |
+
"grad_norm": 3.1999757289886475,
|
1960 |
+
"learning_rate": 0.00018434229129812418,
|
1961 |
+
"loss": 2.1583,
|
1962 |
+
"step": 279
|
1963 |
+
},
|
1964 |
+
{
|
1965 |
+
"epoch": 0.1692034596064509,
|
1966 |
+
"grad_norm": 3.3717172145843506,
|
1967 |
+
"learning_rate": 0.0001842288273089332,
|
1968 |
+
"loss": 2.0239,
|
1969 |
+
"step": 280
|
1970 |
+
},
|
1971 |
+
{
|
1972 |
+
"epoch": 0.1698077576764739,
|
1973 |
+
"grad_norm": 3.339036464691162,
|
1974 |
+
"learning_rate": 0.00018411498887494396,
|
1975 |
+
"loss": 2.199,
|
1976 |
+
"step": 281
|
1977 |
+
},
|
1978 |
+
{
|
1979 |
+
"epoch": 0.17041205574649695,
|
1980 |
+
"grad_norm": 3.3981027603149414,
|
1981 |
+
"learning_rate": 0.00018400077650223263,
|
1982 |
+
"loss": 2.254,
|
1983 |
+
"step": 282
|
1984 |
+
},
|
1985 |
+
{
|
1986 |
+
"epoch": 0.17101635381652,
|
1987 |
+
"grad_norm": 3.418525457382202,
|
1988 |
+
"learning_rate": 0.0001838861906985379,
|
1989 |
+
"loss": 2.1244,
|
1990 |
+
"step": 283
|
1991 |
+
},
|
1992 |
+
{
|
1993 |
+
"epoch": 0.17162065188654305,
|
1994 |
+
"grad_norm": 3.4555487632751465,
|
1995 |
+
"learning_rate": 0.00018377123197325842,
|
1996 |
+
"loss": 2.2547,
|
1997 |
+
"step": 284
|
1998 |
+
},
|
1999 |
+
{
|
2000 |
+
"epoch": 0.17222494995656606,
|
2001 |
+
"grad_norm": 3.6327109336853027,
|
2002 |
+
"learning_rate": 0.00018365590083745085,
|
2003 |
+
"loss": 2.3695,
|
2004 |
+
"step": 285
|
2005 |
+
},
|
2006 |
+
{
|
2007 |
+
"epoch": 0.1728292480265891,
|
2008 |
+
"grad_norm": 3.622626304626465,
|
2009 |
+
"learning_rate": 0.00018354019780382735,
|
2010 |
+
"loss": 2.2134,
|
2011 |
+
"step": 286
|
2012 |
+
},
|
2013 |
+
{
|
2014 |
+
"epoch": 0.17343354609661216,
|
2015 |
+
"grad_norm": 4.037292957305908,
|
2016 |
+
"learning_rate": 0.0001834241233867533,
|
2017 |
+
"loss": 2.2762,
|
2018 |
+
"step": 287
|
2019 |
+
},
|
2020 |
+
{
|
2021 |
+
"epoch": 0.1740378441666352,
|
2022 |
+
"grad_norm": 3.8968253135681152,
|
2023 |
+
"learning_rate": 0.00018330767810224524,
|
2024 |
+
"loss": 2.2187,
|
2025 |
+
"step": 288
|
2026 |
+
},
|
2027 |
+
{
|
2028 |
+
"epoch": 0.17464214223665822,
|
2029 |
+
"grad_norm": 4.63348388671875,
|
2030 |
+
"learning_rate": 0.0001831908624679683,
|
2031 |
+
"loss": 2.2918,
|
2032 |
+
"step": 289
|
2033 |
+
},
|
2034 |
+
{
|
2035 |
+
"epoch": 0.17524644030668127,
|
2036 |
+
"grad_norm": 4.117985248565674,
|
2037 |
+
"learning_rate": 0.0001830736770032341,
|
2038 |
+
"loss": 2.2636,
|
2039 |
+
"step": 290
|
2040 |
+
},
|
2041 |
+
{
|
2042 |
+
"epoch": 0.1758507383767043,
|
2043 |
+
"grad_norm": 3.8585355281829834,
|
2044 |
+
"learning_rate": 0.0001829561222289984,
|
2045 |
+
"loss": 2.145,
|
2046 |
+
"step": 291
|
2047 |
+
},
|
2048 |
+
{
|
2049 |
+
"epoch": 0.17645503644672736,
|
2050 |
+
"grad_norm": 4.775058269500732,
|
2051 |
+
"learning_rate": 0.00018283819866785853,
|
2052 |
+
"loss": 2.3798,
|
2053 |
+
"step": 292
|
2054 |
+
},
|
2055 |
+
{
|
2056 |
+
"epoch": 0.17705933451675038,
|
2057 |
+
"grad_norm": 4.206576824188232,
|
2058 |
+
"learning_rate": 0.0001827199068440516,
|
2059 |
+
"loss": 2.2302,
|
2060 |
+
"step": 293
|
2061 |
+
},
|
2062 |
+
{
|
2063 |
+
"epoch": 0.17766363258677342,
|
2064 |
+
"grad_norm": 5.961564064025879,
|
2065 |
+
"learning_rate": 0.00018260124728345162,
|
2066 |
+
"loss": 2.6911,
|
2067 |
+
"step": 294
|
2068 |
+
},
|
2069 |
+
{
|
2070 |
+
"epoch": 0.17826793065679647,
|
2071 |
+
"grad_norm": 5.647076606750488,
|
2072 |
+
"learning_rate": 0.00018248222051356754,
|
2073 |
+
"loss": 2.8343,
|
2074 |
+
"step": 295
|
2075 |
+
},
|
2076 |
+
{
|
2077 |
+
"epoch": 0.17887222872681952,
|
2078 |
+
"grad_norm": 5.922065258026123,
|
2079 |
+
"learning_rate": 0.00018236282706354063,
|
2080 |
+
"loss": 2.4506,
|
2081 |
+
"step": 296
|
2082 |
+
},
|
2083 |
+
{
|
2084 |
+
"epoch": 0.17947652679684253,
|
2085 |
+
"grad_norm": 6.84862756729126,
|
2086 |
+
"learning_rate": 0.00018224306746414238,
|
2087 |
+
"loss": 2.8937,
|
2088 |
+
"step": 297
|
2089 |
+
},
|
2090 |
+
{
|
2091 |
+
"epoch": 0.18008082486686558,
|
2092 |
+
"grad_norm": 7.7207746505737305,
|
2093 |
+
"learning_rate": 0.00018212294224777197,
|
2094 |
+
"loss": 2.7428,
|
2095 |
+
"step": 298
|
2096 |
+
},
|
2097 |
+
{
|
2098 |
+
"epoch": 0.18068512293688863,
|
2099 |
+
"grad_norm": 13.893342018127441,
|
2100 |
+
"learning_rate": 0.00018200245194845399,
|
2101 |
+
"loss": 3.5557,
|
2102 |
+
"step": 299
|
2103 |
+
},
|
2104 |
+
{
|
2105 |
+
"epoch": 0.18128942100691167,
|
2106 |
+
"grad_norm": 43.88550567626953,
|
2107 |
+
"learning_rate": 0.00018188159710183594,
|
2108 |
+
"loss": 4.1933,
|
2109 |
+
"step": 300
|
2110 |
+
},
|
2111 |
+
{
|
2112 |
+
"epoch": 0.1818937190769347,
|
2113 |
+
"grad_norm": 2.99881911277771,
|
2114 |
+
"learning_rate": 0.000181760378245186,
|
2115 |
+
"loss": 0.6338,
|
2116 |
+
"step": 301
|
2117 |
+
},
|
2118 |
+
{
|
2119 |
+
"epoch": 0.18249801714695774,
|
2120 |
+
"grad_norm": 2.6720895767211914,
|
2121 |
+
"learning_rate": 0.00018163879591739067,
|
2122 |
+
"loss": 1.2616,
|
2123 |
+
"step": 302
|
2124 |
+
},
|
2125 |
+
{
|
2126 |
+
"epoch": 0.18310231521698078,
|
2127 |
+
"grad_norm": 3.5430455207824707,
|
2128 |
+
"learning_rate": 0.0001815168506589521,
|
2129 |
+
"loss": 1.9207,
|
2130 |
+
"step": 303
|
2131 |
+
},
|
2132 |
+
{
|
2133 |
+
"epoch": 0.18370661328700383,
|
2134 |
+
"grad_norm": 3.131864309310913,
|
2135 |
+
"learning_rate": 0.000181394543011986,
|
2136 |
+
"loss": 2.1036,
|
2137 |
+
"step": 304
|
2138 |
+
},
|
2139 |
+
{
|
2140 |
+
"epoch": 0.18431091135702685,
|
2141 |
+
"grad_norm": 2.913851499557495,
|
2142 |
+
"learning_rate": 0.00018127187352021907,
|
2143 |
+
"loss": 2.2422,
|
2144 |
+
"step": 305
|
2145 |
+
},
|
2146 |
+
{
|
2147 |
+
"epoch": 0.1849152094270499,
|
2148 |
+
"grad_norm": 2.898662567138672,
|
2149 |
+
"learning_rate": 0.0001811488427289866,
|
2150 |
+
"loss": 2.1503,
|
2151 |
+
"step": 306
|
2152 |
+
},
|
2153 |
+
{
|
2154 |
+
"epoch": 0.18551950749707294,
|
2155 |
+
"grad_norm": 2.8844833374023438,
|
2156 |
+
"learning_rate": 0.00018102545118523007,
|
2157 |
+
"loss": 2.3369,
|
2158 |
+
"step": 307
|
2159 |
+
},
|
2160 |
+
{
|
2161 |
+
"epoch": 0.18612380556709596,
|
2162 |
+
"grad_norm": 3.364750623703003,
|
2163 |
+
"learning_rate": 0.00018090169943749476,
|
2164 |
+
"loss": 2.2679,
|
2165 |
+
"step": 308
|
2166 |
+
},
|
2167 |
+
{
|
2168 |
+
"epoch": 0.186728103637119,
|
2169 |
+
"grad_norm": 3.5225651264190674,
|
2170 |
+
"learning_rate": 0.00018077758803592718,
|
2171 |
+
"loss": 2.3331,
|
2172 |
+
"step": 309
|
2173 |
+
},
|
2174 |
+
{
|
2175 |
+
"epoch": 0.18733240170714205,
|
2176 |
+
"grad_norm": 3.346677303314209,
|
2177 |
+
"learning_rate": 0.00018065311753227273,
|
2178 |
+
"loss": 2.309,
|
2179 |
+
"step": 310
|
2180 |
+
},
|
2181 |
+
{
|
2182 |
+
"epoch": 0.1879366997771651,
|
2183 |
+
"grad_norm": 3.386894702911377,
|
2184 |
+
"learning_rate": 0.0001805282884798732,
|
2185 |
+
"loss": 2.0257,
|
2186 |
+
"step": 311
|
2187 |
+
},
|
2188 |
+
{
|
2189 |
+
"epoch": 0.1885409978471881,
|
2190 |
+
"grad_norm": 2.942502737045288,
|
2191 |
+
"learning_rate": 0.00018040310143366446,
|
2192 |
+
"loss": 2.1896,
|
2193 |
+
"step": 312
|
2194 |
+
},
|
2195 |
+
{
|
2196 |
+
"epoch": 0.18914529591721116,
|
2197 |
+
"grad_norm": 3.2558510303497314,
|
2198 |
+
"learning_rate": 0.00018027755695017368,
|
2199 |
+
"loss": 1.828,
|
2200 |
+
"step": 313
|
2201 |
+
},
|
2202 |
+
{
|
2203 |
+
"epoch": 0.1897495939872342,
|
2204 |
+
"grad_norm": 3.073988676071167,
|
2205 |
+
"learning_rate": 0.00018015165558751717,
|
2206 |
+
"loss": 1.9587,
|
2207 |
+
"step": 314
|
2208 |
+
},
|
2209 |
+
{
|
2210 |
+
"epoch": 0.19035389205725725,
|
2211 |
+
"grad_norm": 3.157158374786377,
|
2212 |
+
"learning_rate": 0.00018002539790539773,
|
2213 |
+
"loss": 1.748,
|
2214 |
+
"step": 315
|
2215 |
+
},
|
2216 |
+
{
|
2217 |
+
"epoch": 0.19095819012728027,
|
2218 |
+
"grad_norm": 3.194667100906372,
|
2219 |
+
"learning_rate": 0.00017989878446510215,
|
2220 |
+
"loss": 1.8558,
|
2221 |
+
"step": 316
|
2222 |
+
},
|
2223 |
+
{
|
2224 |
+
"epoch": 0.19156248819730332,
|
2225 |
+
"grad_norm": 2.8696138858795166,
|
2226 |
+
"learning_rate": 0.00017977181582949888,
|
2227 |
+
"loss": 1.8613,
|
2228 |
+
"step": 317
|
2229 |
+
},
|
2230 |
+
{
|
2231 |
+
"epoch": 0.19216678626732636,
|
2232 |
+
"grad_norm": 3.149181842803955,
|
2233 |
+
"learning_rate": 0.0001796444925630353,
|
2234 |
+
"loss": 1.9398,
|
2235 |
+
"step": 318
|
2236 |
+
},
|
2237 |
+
{
|
2238 |
+
"epoch": 0.1927710843373494,
|
2239 |
+
"grad_norm": 3.128167152404785,
|
2240 |
+
"learning_rate": 0.00017951681523173542,
|
2241 |
+
"loss": 1.8389,
|
2242 |
+
"step": 319
|
2243 |
+
},
|
2244 |
+
{
|
2245 |
+
"epoch": 0.19337538240737243,
|
2246 |
+
"grad_norm": 3.1106295585632324,
|
2247 |
+
"learning_rate": 0.0001793887844031972,
|
2248 |
+
"loss": 1.7954,
|
2249 |
+
"step": 320
|
2250 |
+
},
|
2251 |
+
{
|
2252 |
+
"epoch": 0.19397968047739547,
|
2253 |
+
"grad_norm": 3.2423572540283203,
|
2254 |
+
"learning_rate": 0.00017926040064659014,
|
2255 |
+
"loss": 1.9777,
|
2256 |
+
"step": 321
|
2257 |
+
},
|
2258 |
+
{
|
2259 |
+
"epoch": 0.19458397854741852,
|
2260 |
+
"grad_norm": 3.1443405151367188,
|
2261 |
+
"learning_rate": 0.0001791316645326526,
|
2262 |
+
"loss": 1.8808,
|
2263 |
+
"step": 322
|
2264 |
+
},
|
2265 |
+
{
|
2266 |
+
"epoch": 0.19518827661744156,
|
2267 |
+
"grad_norm": 3.0229270458221436,
|
2268 |
+
"learning_rate": 0.00017900257663368963,
|
2269 |
+
"loss": 2.0481,
|
2270 |
+
"step": 323
|
2271 |
+
},
|
2272 |
+
{
|
2273 |
+
"epoch": 0.19579257468746458,
|
2274 |
+
"grad_norm": 3.2192728519439697,
|
2275 |
+
"learning_rate": 0.0001788731375235698,
|
2276 |
+
"loss": 1.8968,
|
2277 |
+
"step": 324
|
2278 |
+
},
|
2279 |
+
{
|
2280 |
+
"epoch": 0.19639687275748763,
|
2281 |
+
"grad_norm": 3.273191213607788,
|
2282 |
+
"learning_rate": 0.00017874334777772327,
|
2283 |
+
"loss": 1.9875,
|
2284 |
+
"step": 325
|
2285 |
+
},
|
2286 |
+
{
|
2287 |
+
"epoch": 0.19700117082751067,
|
2288 |
+
"grad_norm": 3.2770490646362305,
|
2289 |
+
"learning_rate": 0.00017861320797313892,
|
2290 |
+
"loss": 2.0555,
|
2291 |
+
"step": 326
|
2292 |
+
},
|
2293 |
+
{
|
2294 |
+
"epoch": 0.19760546889753372,
|
2295 |
+
"grad_norm": 3.1857221126556396,
|
2296 |
+
"learning_rate": 0.0001784827186883618,
|
2297 |
+
"loss": 2.0772,
|
2298 |
+
"step": 327
|
2299 |
+
},
|
2300 |
+
{
|
2301 |
+
"epoch": 0.19820976696755674,
|
2302 |
+
"grad_norm": 3.428528308868408,
|
2303 |
+
"learning_rate": 0.00017835188050349064,
|
2304 |
+
"loss": 2.1237,
|
2305 |
+
"step": 328
|
2306 |
+
},
|
2307 |
+
{
|
2308 |
+
"epoch": 0.19881406503757978,
|
2309 |
+
"grad_norm": 3.3303983211517334,
|
2310 |
+
"learning_rate": 0.00017822069400017516,
|
2311 |
+
"loss": 2.139,
|
2312 |
+
"step": 329
|
2313 |
+
},
|
2314 |
+
{
|
2315 |
+
"epoch": 0.19941836310760283,
|
2316 |
+
"grad_norm": 3.7317135334014893,
|
2317 |
+
"learning_rate": 0.00017808915976161362,
|
2318 |
+
"loss": 2.1451,
|
2319 |
+
"step": 330
|
2320 |
+
},
|
2321 |
+
{
|
2322 |
+
"epoch": 0.20002266117762588,
|
2323 |
+
"grad_norm": 3.494471788406372,
|
2324 |
+
"learning_rate": 0.00017795727837255015,
|
2325 |
+
"loss": 2.252,
|
2326 |
+
"step": 331
|
2327 |
+
},
|
2328 |
+
{
|
2329 |
+
"epoch": 0.2006269592476489,
|
2330 |
+
"grad_norm": 3.569424867630005,
|
2331 |
+
"learning_rate": 0.00017782505041927216,
|
2332 |
+
"loss": 2.1137,
|
2333 |
+
"step": 332
|
2334 |
+
},
|
2335 |
+
{
|
2336 |
+
"epoch": 0.20123125731767194,
|
2337 |
+
"grad_norm": 3.4209699630737305,
|
2338 |
+
"learning_rate": 0.00017769247648960774,
|
2339 |
+
"loss": 2.0488,
|
2340 |
+
"step": 333
|
2341 |
+
},
|
2342 |
+
{
|
2343 |
+
"epoch": 0.201835555387695,
|
2344 |
+
"grad_norm": 3.602125883102417,
|
2345 |
+
"learning_rate": 0.00017755955717292296,
|
2346 |
+
"loss": 2.1312,
|
2347 |
+
"step": 334
|
2348 |
+
},
|
2349 |
+
{
|
2350 |
+
"epoch": 0.20243985345771803,
|
2351 |
+
"grad_norm": 3.67684268951416,
|
2352 |
+
"learning_rate": 0.00017742629306011944,
|
2353 |
+
"loss": 2.1442,
|
2354 |
+
"step": 335
|
2355 |
+
},
|
2356 |
+
{
|
2357 |
+
"epoch": 0.20304415152774105,
|
2358 |
+
"grad_norm": 4.092548847198486,
|
2359 |
+
"learning_rate": 0.00017729268474363154,
|
2360 |
+
"loss": 2.1001,
|
2361 |
+
"step": 336
|
2362 |
+
},
|
2363 |
+
{
|
2364 |
+
"epoch": 0.2036484495977641,
|
2365 |
+
"grad_norm": 4.0197014808654785,
|
2366 |
+
"learning_rate": 0.0001771587328174239,
|
2367 |
+
"loss": 2.3081,
|
2368 |
+
"step": 337
|
2369 |
+
},
|
2370 |
+
{
|
2371 |
+
"epoch": 0.20425274766778714,
|
2372 |
+
"grad_norm": 3.9904866218566895,
|
2373 |
+
"learning_rate": 0.0001770244378769885,
|
2374 |
+
"loss": 2.1657,
|
2375 |
+
"step": 338
|
2376 |
+
},
|
2377 |
+
{
|
2378 |
+
"epoch": 0.20485704573781016,
|
2379 |
+
"grad_norm": 4.197107315063477,
|
2380 |
+
"learning_rate": 0.0001768898005193425,
|
2381 |
+
"loss": 2.3272,
|
2382 |
+
"step": 339
|
2383 |
+
},
|
2384 |
+
{
|
2385 |
+
"epoch": 0.2054613438078332,
|
2386 |
+
"grad_norm": 5.174318790435791,
|
2387 |
+
"learning_rate": 0.000176754821343025,
|
2388 |
+
"loss": 2.396,
|
2389 |
+
"step": 340
|
2390 |
+
},
|
2391 |
+
{
|
2392 |
+
"epoch": 0.20606564187785625,
|
2393 |
+
"grad_norm": 4.303919792175293,
|
2394 |
+
"learning_rate": 0.0001766195009480949,
|
2395 |
+
"loss": 2.285,
|
2396 |
+
"step": 341
|
2397 |
+
},
|
2398 |
+
{
|
2399 |
+
"epoch": 0.2066699399478793,
|
2400 |
+
"grad_norm": 4.526043891906738,
|
2401 |
+
"learning_rate": 0.0001764838399361279,
|
2402 |
+
"loss": 2.254,
|
2403 |
+
"step": 342
|
2404 |
+
},
|
2405 |
+
{
|
2406 |
+
"epoch": 0.20727423801790232,
|
2407 |
+
"grad_norm": 4.815467357635498,
|
2408 |
+
"learning_rate": 0.00017634783891021393,
|
2409 |
+
"loss": 2.3658,
|
2410 |
+
"step": 343
|
2411 |
+
},
|
2412 |
+
{
|
2413 |
+
"epoch": 0.20787853608792536,
|
2414 |
+
"grad_norm": 4.806483745574951,
|
2415 |
+
"learning_rate": 0.00017621149847495458,
|
2416 |
+
"loss": 2.4033,
|
2417 |
+
"step": 344
|
2418 |
+
},
|
2419 |
+
{
|
2420 |
+
"epoch": 0.2084828341579484,
|
2421 |
+
"grad_norm": 5.406166076660156,
|
2422 |
+
"learning_rate": 0.00017607481923646016,
|
2423 |
+
"loss": 2.2625,
|
2424 |
+
"step": 345
|
2425 |
+
},
|
2426 |
+
{
|
2427 |
+
"epoch": 0.20908713222797146,
|
2428 |
+
"grad_norm": 5.956484794616699,
|
2429 |
+
"learning_rate": 0.0001759378018023473,
|
2430 |
+
"loss": 2.635,
|
2431 |
+
"step": 346
|
2432 |
+
},
|
2433 |
+
{
|
2434 |
+
"epoch": 0.20969143029799447,
|
2435 |
+
"grad_norm": 6.868587493896484,
|
2436 |
+
"learning_rate": 0.00017580044678173592,
|
2437 |
+
"loss": 2.5105,
|
2438 |
+
"step": 347
|
2439 |
+
},
|
2440 |
+
{
|
2441 |
+
"epoch": 0.21029572836801752,
|
2442 |
+
"grad_norm": 7.553473949432373,
|
2443 |
+
"learning_rate": 0.00017566275478524693,
|
2444 |
+
"loss": 2.6961,
|
2445 |
+
"step": 348
|
2446 |
+
},
|
2447 |
+
{
|
2448 |
+
"epoch": 0.21090002643804057,
|
2449 |
+
"grad_norm": 13.07988452911377,
|
2450 |
+
"learning_rate": 0.0001755247264249991,
|
2451 |
+
"loss": 3.5881,
|
2452 |
+
"step": 349
|
2453 |
+
},
|
2454 |
+
{
|
2455 |
+
"epoch": 0.2115043245080636,
|
2456 |
+
"grad_norm": 31.356632232666016,
|
2457 |
+
"learning_rate": 0.0001753863623146066,
|
2458 |
+
"loss": 4.2451,
|
2459 |
+
"step": 350
|
2460 |
+
},
|
2461 |
+
{
|
2462 |
+
"epoch": 0.21210862257808663,
|
2463 |
+
"grad_norm": 3.042705535888672,
|
2464 |
+
"learning_rate": 0.00017524766306917618,
|
2465 |
+
"loss": 0.5812,
|
2466 |
+
"step": 351
|
2467 |
+
},
|
2468 |
+
{
|
2469 |
+
"epoch": 0.21271292064810968,
|
2470 |
+
"grad_norm": 2.7835421562194824,
|
2471 |
+
"learning_rate": 0.0001751086293053045,
|
2472 |
+
"loss": 0.9333,
|
2473 |
+
"step": 352
|
2474 |
+
},
|
2475 |
+
{
|
2476 |
+
"epoch": 0.21331721871813272,
|
2477 |
+
"grad_norm": 2.9173827171325684,
|
2478 |
+
"learning_rate": 0.0001749692616410753,
|
2479 |
+
"loss": 1.7894,
|
2480 |
+
"step": 353
|
2481 |
+
},
|
2482 |
+
{
|
2483 |
+
"epoch": 0.21392151678815577,
|
2484 |
+
"grad_norm": 3.177105665206909,
|
2485 |
+
"learning_rate": 0.00017482956069605668,
|
2486 |
+
"loss": 2.0359,
|
2487 |
+
"step": 354
|
2488 |
+
},
|
2489 |
+
{
|
2490 |
+
"epoch": 0.2145258148581788,
|
2491 |
+
"grad_norm": 3.253769874572754,
|
2492 |
+
"learning_rate": 0.00017468952709129846,
|
2493 |
+
"loss": 2.1539,
|
2494 |
+
"step": 355
|
2495 |
+
},
|
2496 |
+
{
|
2497 |
+
"epoch": 0.21513011292820183,
|
2498 |
+
"grad_norm": 3.295257329940796,
|
2499 |
+
"learning_rate": 0.00017454916144932922,
|
2500 |
+
"loss": 2.22,
|
2501 |
+
"step": 356
|
2502 |
+
},
|
2503 |
+
{
|
2504 |
+
"epoch": 0.21573441099822488,
|
2505 |
+
"grad_norm": 2.9911811351776123,
|
2506 |
+
"learning_rate": 0.0001744084643941536,
|
2507 |
+
"loss": 2.2175,
|
2508 |
+
"step": 357
|
2509 |
+
},
|
2510 |
+
{
|
2511 |
+
"epoch": 0.21633870906824793,
|
2512 |
+
"grad_norm": 3.004169464111328,
|
2513 |
+
"learning_rate": 0.00017426743655124974,
|
2514 |
+
"loss": 2.1925,
|
2515 |
+
"step": 358
|
2516 |
+
},
|
2517 |
+
{
|
2518 |
+
"epoch": 0.21694300713827094,
|
2519 |
+
"grad_norm": 2.8875339031219482,
|
2520 |
+
"learning_rate": 0.0001741260785475661,
|
2521 |
+
"loss": 2.2666,
|
2522 |
+
"step": 359
|
2523 |
+
},
|
2524 |
+
{
|
2525 |
+
"epoch": 0.217547305208294,
|
2526 |
+
"grad_norm": 3.057417154312134,
|
2527 |
+
"learning_rate": 0.00017398439101151905,
|
2528 |
+
"loss": 2.1484,
|
2529 |
+
"step": 360
|
2530 |
+
},
|
2531 |
+
{
|
2532 |
+
"epoch": 0.21815160327831704,
|
2533 |
+
"grad_norm": 2.7903478145599365,
|
2534 |
+
"learning_rate": 0.00017384237457298987,
|
2535 |
+
"loss": 2.2869,
|
2536 |
+
"step": 361
|
2537 |
+
},
|
2538 |
+
{
|
2539 |
+
"epoch": 0.21875590134834008,
|
2540 |
+
"grad_norm": 3.01904559135437,
|
2541 |
+
"learning_rate": 0.00017370002986332193,
|
2542 |
+
"loss": 2.3253,
|
2543 |
+
"step": 362
|
2544 |
+
},
|
2545 |
+
{
|
2546 |
+
"epoch": 0.2193601994183631,
|
2547 |
+
"grad_norm": 3.055483102798462,
|
2548 |
+
"learning_rate": 0.00017355735751531807,
|
2549 |
+
"loss": 2.0748,
|
2550 |
+
"step": 363
|
2551 |
+
},
|
2552 |
+
{
|
2553 |
+
"epoch": 0.21996449748838615,
|
2554 |
+
"grad_norm": 3.1257870197296143,
|
2555 |
+
"learning_rate": 0.00017341435816323756,
|
2556 |
+
"loss": 1.8722,
|
2557 |
+
"step": 364
|
2558 |
+
},
|
2559 |
+
{
|
2560 |
+
"epoch": 0.2205687955584092,
|
2561 |
+
"grad_norm": 3.139169454574585,
|
2562 |
+
"learning_rate": 0.00017327103244279348,
|
2563 |
+
"loss": 2.0349,
|
2564 |
+
"step": 365
|
2565 |
+
},
|
2566 |
+
{
|
2567 |
+
"epoch": 0.22117309362843224,
|
2568 |
+
"grad_norm": 3.2363922595977783,
|
2569 |
+
"learning_rate": 0.00017312738099114973,
|
2570 |
+
"loss": 1.8798,
|
2571 |
+
"step": 366
|
2572 |
+
},
|
2573 |
+
{
|
2574 |
+
"epoch": 0.22177739169845526,
|
2575 |
+
"grad_norm": 3.5106101036071777,
|
2576 |
+
"learning_rate": 0.00017298340444691835,
|
2577 |
+
"loss": 1.9831,
|
2578 |
+
"step": 367
|
2579 |
+
},
|
2580 |
+
{
|
2581 |
+
"epoch": 0.2223816897684783,
|
2582 |
+
"grad_norm": 3.2510836124420166,
|
2583 |
+
"learning_rate": 0.00017283910345015647,
|
2584 |
+
"loss": 1.8261,
|
2585 |
+
"step": 368
|
2586 |
+
},
|
2587 |
+
{
|
2588 |
+
"epoch": 0.22298598783850135,
|
2589 |
+
"grad_norm": 3.1266050338745117,
|
2590 |
+
"learning_rate": 0.0001726944786423637,
|
2591 |
+
"loss": 1.7586,
|
2592 |
+
"step": 369
|
2593 |
+
},
|
2594 |
+
{
|
2595 |
+
"epoch": 0.22359028590852437,
|
2596 |
+
"grad_norm": 3.6328091621398926,
|
2597 |
+
"learning_rate": 0.00017254953066647913,
|
2598 |
+
"loss": 1.9136,
|
2599 |
+
"step": 370
|
2600 |
+
},
|
2601 |
+
{
|
2602 |
+
"epoch": 0.2241945839785474,
|
2603 |
+
"grad_norm": 3.0875422954559326,
|
2604 |
+
"learning_rate": 0.00017240426016687863,
|
2605 |
+
"loss": 1.9292,
|
2606 |
+
"step": 371
|
2607 |
+
},
|
2608 |
+
{
|
2609 |
+
"epoch": 0.22479888204857046,
|
2610 |
+
"grad_norm": 3.426515579223633,
|
2611 |
+
"learning_rate": 0.00017225866778937165,
|
2612 |
+
"loss": 1.9904,
|
2613 |
+
"step": 372
|
2614 |
+
},
|
2615 |
+
{
|
2616 |
+
"epoch": 0.2254031801185935,
|
2617 |
+
"grad_norm": 3.369088649749756,
|
2618 |
+
"learning_rate": 0.00017211275418119876,
|
2619 |
+
"loss": 1.7777,
|
2620 |
+
"step": 373
|
2621 |
+
},
|
2622 |
+
{
|
2623 |
+
"epoch": 0.22600747818861652,
|
2624 |
+
"grad_norm": 3.675102710723877,
|
2625 |
+
"learning_rate": 0.0001719665199910285,
|
2626 |
+
"loss": 1.7818,
|
2627 |
+
"step": 374
|
2628 |
+
},
|
2629 |
+
{
|
2630 |
+
"epoch": 0.22661177625863957,
|
2631 |
+
"grad_norm": 3.5006134510040283,
|
2632 |
+
"learning_rate": 0.00017181996586895454,
|
2633 |
+
"loss": 2.0411,
|
2634 |
+
"step": 375
|
2635 |
+
},
|
2636 |
+
{
|
2637 |
+
"epoch": 0.22661177625863957,
|
2638 |
+
"eval_loss": 2.133070945739746,
|
2639 |
+
"eval_runtime": 29.9007,
|
2640 |
+
"eval_samples_per_second": 93.208,
|
2641 |
+
"eval_steps_per_second": 46.621,
|
2642 |
+
"step": 375
|
2643 |
+
}
|
2644 |
+
],
|
2645 |
+
"logging_steps": 1,
|
2646 |
+
"max_steps": 1500,
|
2647 |
+
"num_input_tokens_seen": 0,
|
2648 |
+
"num_train_epochs": 1,
|
2649 |
+
"save_steps": 375,
|
2650 |
+
"stateful_callbacks": {
|
2651 |
+
"TrainerControl": {
|
2652 |
+
"args": {
|
2653 |
+
"should_epoch_stop": false,
|
2654 |
+
"should_evaluate": false,
|
2655 |
+
"should_log": false,
|
2656 |
+
"should_save": true,
|
2657 |
+
"should_training_stop": false
|
2658 |
+
},
|
2659 |
+
"attributes": {}
|
2660 |
+
}
|
2661 |
+
},
|
2662 |
+
"total_flos": 6395465727737856.0,
|
2663 |
+
"train_batch_size": 2,
|
2664 |
+
"trial_name": null,
|
2665 |
+
"trial_params": null
|
2666 |
+
}
|
last-checkpoint/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4863d894ba3ce228a26c7331f57b4eefeb9c93b592ab53d82b32a503b450e298
|
3 |
+
size 6840
|
last-checkpoint/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|