Training in progress, step 6000, checkpoint

checkpoint-6000/config.json

@@ -0,0 +1,33 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "pad_token_id": 2,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "transformers_version": "4.56.1",
+  "use_cache": true,
+  "vocab_size": 30000
+}

checkpoint-6000/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    2
+  ],
+  "pad_token_id": 2,
+  "transformers_version": "4.56.1"
+}

checkpoint-6000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d5c77b22161f29794e5f6c088d9d488fc0c27c8d3b9779a0026ffcd2b9704fd
+size 435544704

checkpoint-6000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5704dbbc76a707afa24d5ba6f3f04d2390c995f68bb9d96aa32d90ae9198d0e1
+size 871183627

checkpoint-6000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3a48043833cd1270809160bb7d044ad943094686c52276198f046435f01df7d
+size 14645

checkpoint-6000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bb2b51b22f222dc6df63edb791d76de5de25b8bb724e885f8753e34cfb8ae10
+size 1383

checkpoint-6000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e826e054eb0300536fcf81da1e4ac55671fddd262bdd49f79d0623427b30c6a4
+size 1465

checkpoint-6000/special_tokens_map.json

@@ -0,0 +1,8 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "</s>",
+  "sep_token": "<sep>",
+  "unk_token": "<unk>"
+}

checkpoint-6000/tokenizer_config.json

@@ -0,0 +1,62 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sep_token": "<sep>",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk>"
+}

checkpoint-6000/trainer_state.json

@@ -0,0 +1,221 @@
+{
+  "best_global_step": 5456,
+  "best_metric": 2.70704984664917,
+  "best_model_checkpoint": null,
+  "epoch": 12.096774193548388,
+  "eval_steps": 500,
+  "global_step": 6000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0020161290322580645,
+      "grad_norm": 30.756797790527344,
+      "learning_rate": 0.0,
+      "loss": 10.401,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.104658603668213,
+      "learning_rate": 9.900000000000001e-05,
+      "loss": 4.4851,
+      "step": 496
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 3.283313274383545,
+      "eval_runtime": 43.1813,
+      "eval_samples_per_second": 737.634,
+      "eval_steps_per_second": 2.895,
+      "step": 496
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.7726725339889526,
+      "learning_rate": 9.477659574468086e-05,
+      "loss": 3.0363,
+      "step": 992
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2.9778614044189453,
+      "eval_runtime": 43.1404,
+      "eval_samples_per_second": 738.333,
+      "eval_steps_per_second": 2.898,
+      "step": 992
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.8007412552833557,
+      "learning_rate": 8.950000000000001e-05,
+      "loss": 2.809,
+      "step": 1488
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 2.8694076538085938,
+      "eval_runtime": 43.0345,
+      "eval_samples_per_second": 740.15,
+      "eval_steps_per_second": 2.905,
+      "step": 1488
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.7199944853782654,
+      "learning_rate": 8.422340425531914e-05,
+      "loss": 2.6893,
+      "step": 1984
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 2.8081631660461426,
+      "eval_runtime": 43.2375,
+      "eval_samples_per_second": 736.675,
+      "eval_steps_per_second": 2.891,
+      "step": 1984
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.736054003238678,
+      "learning_rate": 7.894680851063831e-05,
+      "loss": 2.6063,
+      "step": 2480
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 2.7678091526031494,
+      "eval_runtime": 43.234,
+      "eval_samples_per_second": 736.735,
+      "eval_steps_per_second": 2.891,
+      "step": 2480
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.7721890807151794,
+      "learning_rate": 7.367021276595744e-05,
+      "loss": 2.5402,
+      "step": 2976
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 2.7430224418640137,
+      "eval_runtime": 43.2401,
+      "eval_samples_per_second": 736.631,
+      "eval_steps_per_second": 2.891,
+      "step": 2976
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.7903856039047241,
+      "learning_rate": 6.83936170212766e-05,
+      "loss": 2.484,
+      "step": 3472
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 2.7245240211486816,
+      "eval_runtime": 43.2231,
+      "eval_samples_per_second": 736.92,
+      "eval_steps_per_second": 2.892,
+      "step": 3472
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.821058452129364,
+      "learning_rate": 6.311702127659575e-05,
+      "loss": 2.4329,
+      "step": 3968
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 2.7159740924835205,
+      "eval_runtime": 43.2592,
+      "eval_samples_per_second": 736.305,
+      "eval_steps_per_second": 2.89,
+      "step": 3968
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.8624472618103027,
+      "learning_rate": 5.7840425531914896e-05,
+      "loss": 2.3857,
+      "step": 4464
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 2.707214117050171,
+      "eval_runtime": 43.2052,
+      "eval_samples_per_second": 737.225,
+      "eval_steps_per_second": 2.893,
+      "step": 4464
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.9084471464157104,
+      "learning_rate": 5.256382978723404e-05,
+      "loss": 2.3406,
+      "step": 4960
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 2.708083391189575,
+      "eval_runtime": 43.2547,
+      "eval_samples_per_second": 736.382,
+      "eval_steps_per_second": 2.89,
+      "step": 4960
+    },
+    {
+      "epoch": 11.0,
+      "grad_norm": 0.9790239334106445,
+      "learning_rate": 4.728723404255319e-05,
+      "loss": 2.2977,
+      "step": 5456
+    },
+    {
+      "epoch": 11.0,
+      "eval_loss": 2.70704984664917,
+      "eval_runtime": 43.2971,
+      "eval_samples_per_second": 735.661,
+      "eval_steps_per_second": 2.887,
+      "step": 5456
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 1.0421918630599976,
+      "learning_rate": 4.201063829787234e-05,
+      "loss": 2.2563,
+      "step": 5952
+    },
+    {
+      "epoch": 12.0,
+      "eval_loss": 2.7153050899505615,
+      "eval_runtime": 43.2544,
+      "eval_samples_per_second": 736.388,
+      "eval_steps_per_second": 2.89,
+      "step": 5952
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 9920,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "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": 1.00279701209088e+17,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-6000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46e2ba21cf0e7d7b4d87938499db7536996f9c5c139a8b98df73441877b501dc
+size 5905