Training in progress, step 2000, checkpoint

last-checkpoint/config.json

@@ -0,0 +1,35 @@
+{
+  "activation_function": "gelu_new",
+  "add_cross_attention": false,
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.05,
+  "bos_token_id": 0,
+  "dtype": "float32",
+  "embd_pdrop": 0.05,
+  "eos_token_id": 0,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 512,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 512,
+  "pad_token_id": 1,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.05,
+  "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,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.13.0",
+  "use_cache": false,
+  "vocab_size": 50277
+}

last-checkpoint/generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 1,
+  "transformers_version": "5.13.0",
+  "use_cache": true
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d14a55a7a001ec56d6e7cc97ff832364798045035293d4c041146fbaa0a507d
+size 496262784

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8cf5ea768afac9afe79d638dfb780cc0ea075e584e54b84d31b5edbbc4c2593
+size 992621963

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5364569e6210839a1caff47d9b08a64d50dda76f4704960ecdead9f41b7df112
+size 14645

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7594d618d6ba19521c7abdc5d9c3d75c88e696a2ccaf3aad9e2ee70281ff7494
+size 1465

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 1000000000,
+  "pad_token": "<|padding|>",
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<|endoftext|>"
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,192 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.04,
+  "eval_steps": 1000,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.002,
+      "grad_norm": 0.728621244430542,
+      "learning_rate": 0.00066,
+      "loss": 7.944070434570312,
+      "step": 100
+    },
+    {
+      "epoch": 0.004,
+      "grad_norm": 0.6194736361503601,
+      "learning_rate": 0.0009999976160274871,
+      "loss": 6.688648071289062,
+      "step": 200
+    },
+    {
+      "epoch": 0.006,
+      "grad_norm": 0.42749303579330444,
+      "learning_rate": 0.000999977956590203,
+      "loss": 6.362667846679687,
+      "step": 300
+    },
+    {
+      "epoch": 0.008,
+      "grad_norm": 0.6455233693122864,
+      "learning_rate": 0.0009999384399149713,
+      "loss": 6.1362109375,
+      "step": 400
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.38843703269958496,
+      "learning_rate": 0.0009998790675712448,
+      "loss": 5.9013720703125,
+      "step": 500
+    },
+    {
+      "epoch": 0.012,
+      "grad_norm": 0.37035471200942993,
+      "learning_rate": 0.000999799841917069,
+      "loss": 5.723118896484375,
+      "step": 600
+    },
+    {
+      "epoch": 0.014,
+      "grad_norm": 0.3410094380378723,
+      "learning_rate": 0.0009997007660989881,
+      "loss": 5.57857666015625,
+      "step": 700
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 0.33731603622436523,
+      "learning_rate": 0.0009995818440519195,
+      "loss": 5.440355224609375,
+      "step": 800
+    },
+    {
+      "epoch": 0.018,
+      "grad_norm": 0.39496415853500366,
+      "learning_rate": 0.0009994430804989986,
+      "loss": 5.352986450195313,
+      "step": 900
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.3883383870124817,
+      "learning_rate": 0.0009992844809513896,
+      "loss": 5.53045166015625,
+      "step": 1000
+    },
+    {
+      "epoch": 0.02,
+      "eval_accuracy": 0.19006987944761863,
+      "eval_loss": 5.351119041442871,
+      "eval_runtime": 5.7942,
+      "eval_samples_per_second": 334.99,
+      "eval_steps_per_second": 21.056,
+      "step": 1000
+    },
+    {
+      "epoch": 0.022,
+      "grad_norm": 0.5580651760101318,
+      "learning_rate": 0.0009991060517080686,
+      "loss": 5.3906793212890625,
+      "step": 1100
+    },
+    {
+      "epoch": 0.024,
+      "grad_norm": 4.792799472808838,
+      "learning_rate": 0.0009989077998555718,
+      "loss": 5.624612426757812,
+      "step": 1200
+    },
+    {
+      "epoch": 0.026,
+      "grad_norm": 5.352905750274658,
+      "learning_rate": 0.0009986897332677144,
+      "loss": 6.0997509765625,
+      "step": 1300
+    },
+    {
+      "epoch": 0.028,
+      "grad_norm": 5.617880344390869,
+      "learning_rate": 0.0009984518606052791,
+      "loss": 7.137509765625,
+      "step": 1400
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 6.961197853088379,
+      "learning_rate": 0.0009981941913156701,
+      "loss": 6.8974456787109375,
+      "step": 1500
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 7.469847679138184,
+      "learning_rate": 0.0009979167356325394,
+      "loss": 6.911260375976562,
+      "step": 1600
+    },
+    {
+      "epoch": 0.034,
+      "grad_norm": 21.165908813476562,
+      "learning_rate": 0.0009976195045753797,
+      "loss": 6.70553466796875,
+      "step": 1700
+    },
+    {
+      "epoch": 0.036,
+      "grad_norm": 10.395805358886719,
+      "learning_rate": 0.0009973025099490876,
+      "loss": 6.70605712890625,
+      "step": 1800
+    },
+    {
+      "epoch": 0.038,
+      "grad_norm": 2.6919143199920654,
+      "learning_rate": 0.0009969657643434933,
+      "loss": 6.605548706054687,
+      "step": 1900
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 470.6007080078125,
+      "learning_rate": 0.0009966092811328612,
+      "loss": 6.552777099609375,
+      "step": 2000
+    },
+    {
+      "epoch": 0.04,
+      "eval_accuracy": 0.10447133692459855,
+      "eval_loss": 6.653895378112793,
+      "eval_runtime": 5.1208,
+      "eval_samples_per_second": 379.042,
+      "eval_steps_per_second": 23.824,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 50000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9223372036854775807,
+  "save_steps": 2000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.271008768e+16,
+  "train_batch_size": 120,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc2fadc166c1876d75b4f91077944f22473b7782e4d604a36addc50eb7aa83ec
+size 5201