Upload folder using huggingface_hub

adapter_config.json

@@ -2,7 +2,7 @@
   "alpha_pattern": {},
   "auto_mapping": null,
   "base_model_name_or_path": "HuggingFaceM4/Idefics3-8B-Llama3",
-  "bias": "none",
+  "bias": "all",
   "corda_config": null,
   "eva_config": null,
   "exclude_modules": null,
@@ -13,24 +13,24 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 32,
   "lora_bias": false,
-  "lora_dropout": 0.05,
+  "lora_dropout": 0.0,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "down_proj",
     "o_proj",
-    "q_proj",
     "v_proj",
-    "up_proj",
-    "gate_proj"
+    "gate_proj",
+    "q_proj",
+    "down_proj",
+    "k_proj",
+    "up_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae4abc84cc8c2b64dabab4d6cb1f76202fec50244b34537a5e638055ae6efade
-size 89947240
+oid sha256:40e600b0bbcef2169f37655ebaef91ee7bc8d0571053e96c7fed9e7cfda40e50
+size 181121328

checkpoint-225/README.md

@@ -0,0 +1,202 @@
+---
+base_model: HuggingFaceM4/Idefics3-8B-Llama3
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- 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. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+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).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.1

checkpoint-225/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "HuggingFaceM4/Idefics3-8B-Llama3",
+  "bias": "all",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "v_proj",
+    "gate_proj",
+    "q_proj",
+    "down_proj",
+    "k_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-225/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5aa26b8b87ca625b5a0827013bff387226ac29e78a40c4659861905cce9b439d
+size 181121328

checkpoint-225/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24c1346ccacf71fb04ed36e123abdfe13986e054d757866ce61a5034e3b505d4
+size 94105734

checkpoint-225/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9a6944c405a002fce05f295d08ea6650e2e2ad6dbf5d6da1e9053f7bf7f5827
+size 14244

checkpoint-225/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c9084c5d6f1a97cccd83cb57fb7f893c9f475795fa71928d0c4d4dfb57f472a
+size 1064

checkpoint-225/trainer_state.json

@@ -0,0 +1,188 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.0,
+  "eval_steps": 500,
+  "global_step": 225,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.5595075488090515,
+      "learning_rate": 0.000482,
+      "loss": 0.4307,
+      "step": 10
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.566727340221405,
+      "learning_rate": 0.000462,
+      "loss": 0.0524,
+      "step": 20
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.2078760862350464,
+      "learning_rate": 0.000442,
+      "loss": 0.026,
+      "step": 30
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.25045984983444214,
+      "learning_rate": 0.000422,
+      "loss": 0.0261,
+      "step": 40
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.20396892726421356,
+      "learning_rate": 0.000402,
+      "loss": 0.0199,
+      "step": 50
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.08542954921722412,
+      "learning_rate": 0.000382,
+      "loss": 0.028,
+      "step": 60
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.17754589021205902,
+      "learning_rate": 0.000362,
+      "loss": 0.0154,
+      "step": 70
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 0.10964138805866241,
+      "learning_rate": 0.000342,
+      "loss": 0.0158,
+      "step": 80
+    },
+    {
+      "epoch": 3.6,
+      "grad_norm": 1.3268883228302002,
+      "learning_rate": 0.000322,
+      "loss": 0.0156,
+      "step": 90
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.16379483044147491,
+      "learning_rate": 0.000302,
+      "loss": 0.0157,
+      "step": 100
+    },
+    {
+      "epoch": 4.4,
+      "grad_norm": 0.1214568242430687,
+      "learning_rate": 0.00028199999999999997,
+      "loss": 0.0125,
+      "step": 110
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 0.13405731320381165,
+      "learning_rate": 0.000262,
+      "loss": 0.0129,
+      "step": 120
+    },
+    {
+      "epoch": 5.2,
+      "grad_norm": 0.016486013308167458,
+      "learning_rate": 0.000242,
+      "loss": 0.0125,
+      "step": 130
+    },
+    {
+      "epoch": 5.6,
+      "grad_norm": 1.5530146360397339,
+      "learning_rate": 0.000222,
+      "loss": 0.0117,
+      "step": 140
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.1322641223669052,
+      "learning_rate": 0.000202,
+      "loss": 0.0137,
+      "step": 150
+    },
+    {
+      "epoch": 6.4,
+      "grad_norm": 0.15241874754428864,
+      "learning_rate": 0.000182,
+      "loss": 0.0108,
+      "step": 160
+    },
+    {
+      "epoch": 6.8,
+      "grad_norm": 0.05570691078901291,
+      "learning_rate": 0.000162,
+      "loss": 0.0108,
+      "step": 170
+    },
+    {
+      "epoch": 7.2,
+      "grad_norm": 0.059169329702854156,
+      "learning_rate": 0.00014199999999999998,
+      "loss": 0.0113,
+      "step": 180
+    },
+    {
+      "epoch": 7.6,
+      "grad_norm": 0.0516737699508667,
+      "learning_rate": 0.000122,
+      "loss": 0.0093,
+      "step": 190
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.22752004861831665,
+      "learning_rate": 0.000102,
+      "loss": 0.0097,
+      "step": 200
+    },
+    {
+      "epoch": 8.4,
+      "grad_norm": 0.28640028834342957,
+      "learning_rate": 8.2e-05,
+      "loss": 0.0092,
+      "step": 210
+    },
+    {
+      "epoch": 8.8,
+      "grad_norm": 0.053172893822193146,
+      "learning_rate": 6.2e-05,
+      "loss": 0.0087,
+      "step": 220
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 250,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.040235937990537e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-225/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:435bed0dcc62595ba4da347c71211352cfdde9d5573c9faf4e4c6851dcd6681f
+size 5368

checkpoint-250/README.md

@@ -0,0 +1,202 @@
+---
+base_model: HuggingFaceM4/Idefics3-8B-Llama3
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- 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. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+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).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.1

checkpoint-250/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "HuggingFaceM4/Idefics3-8B-Llama3",
+  "bias": "all",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "v_proj",
+    "gate_proj",
+    "q_proj",
+    "down_proj",
+    "k_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-250/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40e600b0bbcef2169f37655ebaef91ee7bc8d0571053e96c7fed9e7cfda40e50
+size 181121328

checkpoint-250/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4743bf97dc3dacb4eae5edcb345192254c6d041ef862aacbab8a65b6d24cd811
+size 94105734

checkpoint-250/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b11a10749bfb1630d95eef94125f4590e8610c579d217d1f158e71ce518d72b
+size 14244

checkpoint-250/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a9cac68c495800a4bdcb66ffc3cc1e8f81886b9e59bf61baf66314bb15b9839
+size 1064

checkpoint-250/trainer_state.json

@@ -0,0 +1,209 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 250,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.5595075488090515,
+      "learning_rate": 0.000482,
+      "loss": 0.4307,
+      "step": 10
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.566727340221405,
+      "learning_rate": 0.000462,
+      "loss": 0.0524,
+      "step": 20
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.2078760862350464,
+      "learning_rate": 0.000442,
+      "loss": 0.026,
+      "step": 30
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.25045984983444214,
+      "learning_rate": 0.000422,
+      "loss": 0.0261,
+      "step": 40
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.20396892726421356,
+      "learning_rate": 0.000402,
+      "loss": 0.0199,
+      "step": 50
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.08542954921722412,
+      "learning_rate": 0.000382,
+      "loss": 0.028,
+      "step": 60
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.17754589021205902,
+      "learning_rate": 0.000362,
+      "loss": 0.0154,
+      "step": 70
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 0.10964138805866241,
+      "learning_rate": 0.000342,
+      "loss": 0.0158,
+      "step": 80
+    },
+    {
+      "epoch": 3.6,
+      "grad_norm": 1.3268883228302002,
+      "learning_rate": 0.000322,
+      "loss": 0.0156,
+      "step": 90
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.16379483044147491,
+      "learning_rate": 0.000302,
+      "loss": 0.0157,
+      "step": 100
+    },
+    {
+      "epoch": 4.4,
+      "grad_norm": 0.1214568242430687,
+      "learning_rate": 0.00028199999999999997,
+      "loss": 0.0125,
+      "step": 110
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 0.13405731320381165,
+      "learning_rate": 0.000262,
+      "loss": 0.0129,
+      "step": 120
+    },
+    {
+      "epoch": 5.2,
+      "grad_norm": 0.016486013308167458,
+      "learning_rate": 0.000242,
+      "loss": 0.0125,
+      "step": 130
+    },
+    {
+      "epoch": 5.6,
+      "grad_norm": 1.5530146360397339,
+      "learning_rate": 0.000222,
+      "loss": 0.0117,
+      "step": 140
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.1322641223669052,
+      "learning_rate": 0.000202,
+      "loss": 0.0137,
+      "step": 150
+    },
+    {
+      "epoch": 6.4,
+      "grad_norm": 0.15241874754428864,
+      "learning_rate": 0.000182,
+      "loss": 0.0108,
+      "step": 160
+    },
+    {
+      "epoch": 6.8,
+      "grad_norm": 0.05570691078901291,
+      "learning_rate": 0.000162,
+      "loss": 0.0108,
+      "step": 170
+    },
+    {
+      "epoch": 7.2,
+      "grad_norm": 0.059169329702854156,
+      "learning_rate": 0.00014199999999999998,
+      "loss": 0.0113,
+      "step": 180
+    },
+    {
+      "epoch": 7.6,
+      "grad_norm": 0.0516737699508667,
+      "learning_rate": 0.000122,
+      "loss": 0.0093,
+      "step": 190
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.22752004861831665,
+      "learning_rate": 0.000102,
+      "loss": 0.0097,
+      "step": 200
+    },
+    {
+      "epoch": 8.4,
+      "grad_norm": 0.28640028834342957,
+      "learning_rate": 8.2e-05,
+      "loss": 0.0092,
+      "step": 210
+    },
+    {
+      "epoch": 8.8,
+      "grad_norm": 0.053172893822193146,
+      "learning_rate": 6.2e-05,
+      "loss": 0.0087,
+      "step": 220
+    },
+    {
+      "epoch": 9.2,
+      "grad_norm": 0.0015004288870841265,
+      "learning_rate": 4.2000000000000004e-05,
+      "loss": 0.0091,
+      "step": 230
+    },
+    {
+      "epoch": 9.6,
+      "grad_norm": 0.0008665521745570004,
+      "learning_rate": 2.2e-05,
+      "loss": 0.0087,
+      "step": 240
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.002254044869914651,
+      "learning_rate": 2e-06,
+      "loss": 0.0088,
+      "step": 250
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 250,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.1558177088783744e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-250/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:435bed0dcc62595ba4da347c71211352cfdde9d5573c9faf4e4c6851dcd6681f
+size 5368

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:757be1c658f5bc062ea058da5a2384ef0334c580b541f392e89986315f721679
-size 17210683
+oid sha256:d1b5ea123f25178b4d498f9fd5dafe3e1356c7d179ffeb792659eaee8972b8a6
+size 17210501