Training in progress, step 1000, checkpoint

last-checkpoint/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "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,
+  "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,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.2",
+  "use_cache": true,
+  "vocab_size": 50259
+}

last-checkpoint/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.40.2"
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c1708023a847ae164ee351bba31de2495e36cb2cd1aaa6bc0c74346a4e2a3cf
+size 497780352

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48370983c9c42d1666f1f7180c1d0e86074efea24546c4403893540848930c00
+size 995617914

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6825ef08a8945e3a69ff427bf9010a71582186c7086628a430377a6fbcb76689
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c54969c1d926cbd9391b4a8e9eb5650cba3c5b704a2a98698e1fb56cf63260a
+size 1064

last-checkpoint/trainer_state.json

@@ -0,0 +1,75 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 200,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2,
+      "eval_loss": 0.07517029345035553,
+      "eval_runtime": 37.992,
+      "eval_samples_per_second": 421.142,
+      "eval_steps_per_second": 6.58,
+      "step": 200
+    },
+    {
+      "epoch": 0.4,
+      "eval_loss": 0.21885745227336884,
+      "eval_runtime": 37.9737,
+      "eval_samples_per_second": 421.344,
+      "eval_steps_per_second": 6.583,
+      "step": 400
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 205354.109375,
+      "learning_rate": 4.877641290737884e-05,
+      "loss": 0.3926,
+      "step": 500
+    },
+    {
+      "epoch": 0.6,
+      "eval_loss": 1.307199478149414,
+      "eval_runtime": 37.7639,
+      "eval_samples_per_second": 423.685,
+      "eval_steps_per_second": 6.62,
+      "step": 600
+    },
+    {
+      "epoch": 0.8,
+      "eval_loss": 0.062136366963386536,
+      "eval_runtime": 37.7282,
+      "eval_samples_per_second": 424.086,
+      "eval_steps_per_second": 6.626,
+      "step": 800
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.6423090696334839,
+      "learning_rate": 4.522542485937369e-05,
+      "loss": 0.9884,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.031570661813020706,
+      "eval_runtime": 37.8801,
+      "eval_samples_per_second": 422.385,
+      "eval_steps_per_second": 6.6,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 1000,
+  "total_flos": 4180672512000000.0,
+  "train_batch_size": 64,
+  "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:d1f0fcad3e74386ffcf1917836bd60c8d585b4f88d87c9181c320cc9fefea09b
+size 4984