Training in progress, step 500, checkpoint

last-checkpoint/config.json

@@ -0,0 +1,33 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 2,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 3,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 512,
+  "n_head": 8,
+  "n_inner": null,
+  "n_layer": 6,
+  "n_positions": 1024,
+  "pad_token_id": 0,
+  "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,
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.3",
+  "use_cache": true,
+  "vocab_size": 2748
+}

last-checkpoint/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 3,
+  "pad_token_id": 0,
+  "transformers_version": "4.52.3"
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f95c23974ed9109b85d1dad46b75fc294d57305fa7210035c0b8f9d6d02471c8
+size 83393928

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73ca5659e648d8d2948c2a5236ec358ca29f5a01082e4ad9696138a21a331db0
+size 166834490

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fab47d19446cd54935782c0ac0c7342531b306e31812fb709d49481db05d461
+size 13990

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff6c50a5de085f119dc1e92af1ad0ce825f5b55602192739818f51a65a78e8d6
+size 1064

last-checkpoint/special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<bos>",
+  "eos_token": "<eos>",
+  "pad_token": "<pad>"
+}

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,51 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<eos>",
+      "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
+    }
+  },
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "PreTrainedTokenizer"
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,77 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.0094758886014536,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0018951777202907204,
+      "grad_norm": 1.4995942115783691,
+      "learning_rate": 4.9968729863927535e-05,
+      "loss": 2.9094,
+      "step": 100
+    },
+    {
+      "epoch": 0.0037903554405814407,
+      "grad_norm": 1.0977892875671387,
+      "learning_rate": 4.993714386789473e-05,
+      "loss": 1.5183,
+      "step": 200
+    },
+    {
+      "epoch": 0.005685533160872161,
+      "grad_norm": 1.0429936647415161,
+      "learning_rate": 4.990555787186194e-05,
+      "loss": 1.2885,
+      "step": 300
+    },
+    {
+      "epoch": 0.007580710881162881,
+      "grad_norm": 1.138353705406189,
+      "learning_rate": 4.987397187582913e-05,
+      "loss": 1.168,
+      "step": 400
+    },
+    {
+      "epoch": 0.0094758886014536,
+      "grad_norm": 1.1610647439956665,
+      "learning_rate": 4.984238587979634e-05,
+      "loss": 1.0943,
+      "step": 500
+    },
+    {
+      "epoch": 0.0094758886014536,
+      "eval_loss": 1.04551362991333,
+      "eval_runtime": 12329.9845,
+      "eval_samples_per_second": 7.608,
+      "eval_steps_per_second": 3.804,
+      "step": 500
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 158298,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 512075305648128.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95c474823f5d7428b2a7c3ff152cd86946f2d74f1036f568aa7833b45b79dc5f
+size 5304