End of training

README.md

@@ -0,0 +1,76 @@
+---
+library_name: transformers
+license: mit
+base_model: gpt2-medium
+tags:
+- generated_from_trainer
+model-index:
+- name: chessgpt-medium-l
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# chessgpt-medium-l
+
+This model is a fine-tuned version of [gpt2-medium](https://huggingface.co/gpt2-medium) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7634
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0003
+- train_batch_size: 16
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.2
+- num_epochs: 1
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 1.4326        | 0.064 | 1000  | 1.3596          |
+| 1.2424        | 0.128 | 2000  | 1.1829          |
+| 1.1278        | 0.192 | 3000  | 1.0753          |
+| 1.0296        | 0.256 | 4000  | 0.9877          |
+| 0.9605        | 0.32  | 5000  | 0.9224          |
+| 0.9193        | 0.384 | 6000  | 0.8874          |
+| 0.8911        | 0.448 | 7000  | 0.8600          |
+| 0.8707        | 0.512 | 8000  | 0.8405          |
+| 0.8521        | 0.576 | 9000  | 0.8221          |
+| 0.8391        | 0.64  | 10000 | 0.8089          |
+| 0.8242        | 0.704 | 11000 | 0.7972          |
+| 0.8146        | 0.768 | 12000 | 0.7858          |
+| 0.8047        | 0.832 | 13000 | 0.7769          |
+| 0.7974        | 0.896 | 14000 | 0.7701          |
+| 0.7916        | 0.96  | 15000 | 0.7651          |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.4.0+cu121
+- Datasets 3.0.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.7633727192878723,
+    "eval_runtime": 465.9005,
+    "eval_samples": 125000,
+    "eval_samples_per_second": 53.66,
+    "eval_steps_per_second": 6.707,
+    "perplexity": 2.145500201330361,
+    "total_flos": 6.467778978579087e+17,
+    "train_loss": 0.0316199453125,
+    "train_runtime": 3118.7762,
+    "train_samples": 1000000,
+    "train_samples_per_second": 320.639,
+    "train_steps_per_second": 5.01
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.7633727192878723,
+    "eval_runtime": 465.9005,
+    "eval_samples": 125000,
+    "eval_samples_per_second": 53.66,
+    "eval_steps_per_second": 6.707,
+    "perplexity": 2.145500201330361
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.44.2"
+}

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:685258b47a970bfe9467bcf03371857ad301c7d5967bd13fdcf9b63a4b7f07c3
+oid sha256:41a75d7e56e510ebd0246ce6077f7354b2bd08eea3d6dee1c2821fad0b717483
 size 1419322880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a27ab9bc2f3e5301bc43d71cfe5e9f7d5a9447619346d539abc10f2fb574cf8
+oid sha256:cdda7b415287871e7541ee48a885b2f659eb3612ac4d4d7b96967e2bc6a4b09e
 size 2838829242

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd3d65bc3b9de79f26666d6f793663ce72713a82aa04257092654a9c541bf476
+oid sha256:11aeff85cf180f6e39d390f0c73b4191a0057f4e10e837cdc8d0d52f2ba5ed37
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee1da4f693ff8640ff89acd2b81e92a2853169d3dced27f669df5cb551c1a946
+oid sha256:4e6cddd194702ba3d5358e4dca8328bb3cc2b0f59539c04abda492cb8ee76e8b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0,
+  "epoch": 0.96,
   "eval_steps": 1000,
-  "global_step": 15625,
+  "global_step": 15000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -967,41 +967,6 @@
       "eval_samples_per_second": 53.702,
       "eval_steps_per_second": 6.713,
       "step": 15000
-    },
-    {
-      "epoch": 0.968,
-      "grad_norm": 0.30145466327667236,
-      "learning_rate": 1.2095999999999999e-05,
-      "loss": 0.794,
-      "step": 15125
-    },
-    {
-      "epoch": 0.976,
-      "grad_norm": 0.25297385454177856,
-      "learning_rate": 9.095999999999999e-06,
-      "loss": 0.7907,
-      "step": 15250
-    },
-    {
-      "epoch": 0.984,
-      "grad_norm": 0.24243755638599396,
-      "learning_rate": 6.096e-06,
-      "loss": 0.7901,
-      "step": 15375
-    },
-    {
-      "epoch": 0.992,
-      "grad_norm": 0.25872665643692017,
-      "learning_rate": 3.0959999999999997e-06,
-      "loss": 0.7887,
-      "step": 15500
-    },
-    {
-      "epoch": 1.0,
-      "grad_norm": 0.28159773349761963,
-      "learning_rate": 9.6e-08,
-      "loss": 0.789,
-      "step": 15625
     }
   ],
   "logging_steps": 125,
@@ -1016,12 +981,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 6.467778978579087e+17,
+  "total_flos": 6.209723238342328e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3458fc15406d987c9decf8a63c702fd276fdb861db3b557185f99e310704375e
+oid sha256:be9e8ac997489bca24294854a2e24893ea0dbb73701c8abc575eda07c340f6fc
 size 5176

runs/Sep16_13-23-58_13ea5bdc15fa/events.out.tfevents.1726497240.13ea5bdc15fa.1753.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09e7e4cf7b275b8cdfeebb58237571c1a9723517914ba4c43010e097e57011d5
+size 359

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 6.467778978579087e+17,
+    "train_loss": 0.0316199453125,
+    "train_runtime": 3118.7762,
+    "train_samples": 1000000,
+    "train_samples_per_second": 320.639,
+    "train_steps_per_second": 5.01
+}