Training in progress, step 3000, checkpoint

checkpoint-3000/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-3000/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-3000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6995e7df85dd694d3683c4f8dfeb3c8a116e78cdc5208f31c70ec458e1d63fe
+size 435544704

checkpoint-3000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b98f729f0604f8c8beec3a58c6153782df3217dc0005ae6ff2165abfe4df278
+size 871183627

checkpoint-3000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4d84e866bdccae5d7bed1498db74638e69f4233e0122978593a6dd0c0db5a72
+size 14645

checkpoint-3000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ac1c46a2776d12775d23d0f587efc112188137ce2140da35bc15d301c9f620e
+size 1383

checkpoint-3000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74a7dd27b9f5e68a35c8236742c68cf323a4869b4b3c4d517ecbf7bf0f7eae56
+size 1465

checkpoint-3000/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-3000/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-3000/trainer_state.json

@@ -0,0 +1,146 @@
+{
+  "best_global_step": 2744,
+  "best_metric": 5.209555625915527,
+  "best_model_checkpoint": null,
+  "epoch": 7.653061224489796,
+  "eval_steps": 500,
+  "global_step": 3000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.002551020408163265,
+      "grad_norm": 15.366922378540039,
+      "learning_rate": 0.0,
+      "loss": 10.3593,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.136745810508728,
+      "learning_rate": 7.82e-05,
+      "loss": 6.8997,
+      "step": 392
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 5.930075645446777,
+      "eval_runtime": 19.2442,
+      "eval_samples_per_second": 1310.054,
+      "eval_steps_per_second": 5.144,
+      "step": 392
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.7629371285438538,
+      "learning_rate": 9.613387978142077e-05,
+      "loss": 5.6835,
+      "step": 784
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 5.580772876739502,
+      "eval_runtime": 19.2272,
+      "eval_samples_per_second": 1311.214,
+      "eval_steps_per_second": 5.149,
+      "step": 784
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.7121202945709229,
+      "learning_rate": 9.077868852459017e-05,
+      "loss": 5.4552,
+      "step": 1176
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 5.4481611251831055,
+      "eval_runtime": 19.3497,
+      "eval_samples_per_second": 1302.914,
+      "eval_steps_per_second": 5.116,
+      "step": 1176
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.7350335717201233,
+      "learning_rate": 8.542349726775956e-05,
+      "loss": 5.3278,
+      "step": 1568
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 5.3602681159973145,
+      "eval_runtime": 19.3612,
+      "eval_samples_per_second": 1302.139,
+      "eval_steps_per_second": 5.113,
+      "step": 1568
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.7943153381347656,
+      "learning_rate": 8.006830601092896e-05,
+      "loss": 5.2293,
+      "step": 1960
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 5.298644542694092,
+      "eval_runtime": 19.3463,
+      "eval_samples_per_second": 1303.146,
+      "eval_steps_per_second": 5.117,
+      "step": 1960
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.7913275361061096,
+      "learning_rate": 7.471311475409837e-05,
+      "loss": 5.1439,
+      "step": 2352
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 5.250115871429443,
+      "eval_runtime": 19.5931,
+      "eval_samples_per_second": 1286.731,
+      "eval_steps_per_second": 5.053,
+      "step": 2352
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.8166405558586121,
+      "learning_rate": 6.935792349726776e-05,
+      "loss": 5.0666,
+      "step": 2744
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 5.209555625915527,
+      "eval_runtime": 19.413,
+      "eval_samples_per_second": 1298.667,
+      "eval_steps_per_second": 5.1,
+      "step": 2744
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7840,
+  "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": 5.0127373910016e+16,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-3000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a299074583b59d2a7fedd127ce64d8d9c54c8b2bf68352df770e3cf50f5910b
+size 5905