Upload folder using huggingface_hub

checkpoint-11110/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81095f0df2f882f9eda50582dbe6d35c3fcfd0313d93692ab14b67b2c5068903
+size 1567531953

checkpoint-11110/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bbe11950022b53f8820e499a57bbaac87e217ba4682e1486ee79793f4d0329b
+size 1281583254

checkpoint-11110/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:175f75c932dcdb99bdfe532e7f70d93099e7fd8aa9c996f5ee65482c01753ccc
+size 14244

checkpoint-11110/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c13eaf49e2347ca3e373d8fa1ac3b0078f46477102d5bac9947d4e1d1f45a43e
+size 1064

checkpoint-11110/trainer_state.json

@@ -0,0 +1,188 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 11110,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0450070323488045,
+      "grad_norm": 6.08460807800293,
+      "learning_rate": 4.7754275427542756e-05,
+      "loss": 8.048,
+      "step": 500
+    },
+    {
+      "epoch": 0.090014064697609,
+      "grad_norm": 4.277126312255859,
+      "learning_rate": 4.55040504050405e-05,
+      "loss": 5.3625,
+      "step": 1000
+    },
+    {
+      "epoch": 0.1350210970464135,
+      "grad_norm": 5.009870529174805,
+      "learning_rate": 4.325382538253826e-05,
+      "loss": 4.9578,
+      "step": 1500
+    },
+    {
+      "epoch": 0.180028129395218,
+      "grad_norm": 5.196658134460449,
+      "learning_rate": 4.1003600360036004e-05,
+      "loss": 4.8138,
+      "step": 2000
+    },
+    {
+      "epoch": 0.2250351617440225,
+      "grad_norm": 4.943167686462402,
+      "learning_rate": 3.875337533753375e-05,
+      "loss": 4.742,
+      "step": 2500
+    },
+    {
+      "epoch": 0.270042194092827,
+      "grad_norm": 5.109597206115723,
+      "learning_rate": 3.6503150315031505e-05,
+      "loss": 4.6585,
+      "step": 3000
+    },
+    {
+      "epoch": 0.3150492264416315,
+      "grad_norm": 5.571631908416748,
+      "learning_rate": 3.425292529252925e-05,
+      "loss": 4.5701,
+      "step": 3500
+    },
+    {
+      "epoch": 0.360056258790436,
+      "grad_norm": 4.485278606414795,
+      "learning_rate": 3.2002700270027e-05,
+      "loss": 4.5362,
+      "step": 4000
+    },
+    {
+      "epoch": 0.4050632911392405,
+      "grad_norm": 4.663172721862793,
+      "learning_rate": 2.9752475247524754e-05,
+      "loss": 4.508,
+      "step": 4500
+    },
+    {
+      "epoch": 0.450070323488045,
+      "grad_norm": 5.958630084991455,
+      "learning_rate": 2.75022502250225e-05,
+      "loss": 4.5017,
+      "step": 5000
+    },
+    {
+      "epoch": 0.49507735583684953,
+      "grad_norm": 4.199305057525635,
+      "learning_rate": 2.525202520252025e-05,
+      "loss": 4.4644,
+      "step": 5500
+    },
+    {
+      "epoch": 0.540084388185654,
+      "grad_norm": 4.755779266357422,
+      "learning_rate": 2.3001800180018002e-05,
+      "loss": 4.4374,
+      "step": 6000
+    },
+    {
+      "epoch": 0.5850914205344585,
+      "grad_norm": 4.645013332366943,
+      "learning_rate": 2.0751575157515752e-05,
+      "loss": 4.4243,
+      "step": 6500
+    },
+    {
+      "epoch": 0.630098452883263,
+      "grad_norm": 4.718759536743164,
+      "learning_rate": 1.85013501350135e-05,
+      "loss": 4.438,
+      "step": 7000
+    },
+    {
+      "epoch": 0.6751054852320675,
+      "grad_norm": 5.006588935852051,
+      "learning_rate": 1.625112511251125e-05,
+      "loss": 4.4076,
+      "step": 7500
+    },
+    {
+      "epoch": 0.720112517580872,
+      "grad_norm": 4.906742572784424,
+      "learning_rate": 1.4000900090009e-05,
+      "loss": 4.4127,
+      "step": 8000
+    },
+    {
+      "epoch": 0.7651195499296765,
+      "grad_norm": 4.846324443817139,
+      "learning_rate": 1.1750675067506751e-05,
+      "loss": 4.403,
+      "step": 8500
+    },
+    {
+      "epoch": 0.810126582278481,
+      "grad_norm": 4.417417049407959,
+      "learning_rate": 9.500450045004502e-06,
+      "loss": 4.3616,
+      "step": 9000
+    },
+    {
+      "epoch": 0.8551336146272855,
+      "grad_norm": 4.223020076751709,
+      "learning_rate": 7.250225022502251e-06,
+      "loss": 4.3806,
+      "step": 9500
+    },
+    {
+      "epoch": 0.90014064697609,
+      "grad_norm": 3.9058163166046143,
+      "learning_rate": 5e-06,
+      "loss": 4.3992,
+      "step": 10000
+    },
+    {
+      "epoch": 0.9451476793248945,
+      "grad_norm": 4.505509376525879,
+      "learning_rate": 2.7497749774977497e-06,
+      "loss": 4.4103,
+      "step": 10500
+    },
+    {
+      "epoch": 0.9901547116736991,
+      "grad_norm": 4.995821952819824,
+      "learning_rate": 4.995499549954995e-07,
+      "loss": 4.3893,
+      "step": 11000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 11110,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 99999999,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-11110/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6074fcfa92e42f72f8cfc1a35eb2850ce9a610c3a6f34d393df2270b2917dbc6
+size 5240

checkpoint-15/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:711633530f359dd586713752c8702d8d8d738c777f742c8564113d351a4cb3d4
+size 1567531953

checkpoint-15/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b54e8c29845520332f20a4230cb8e6c18d6f6c6279edca3d69b28039ba50b573
+size 1281583254

checkpoint-15/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a106833e0b97235cc7b776f0aa805dd347eec5b445d60a85e243f7225dbfe629
+size 14244

checkpoint-15/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d0facd13ec6092c2b43cce23b0a73463bc00999cd16da7cbf795867dc294419
+size 1064

checkpoint-15/trainer_state.json

@@ -0,0 +1,33 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 15,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [],
+  "logging_steps": 500,
+  "max_steps": 15,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 99999999,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-15/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6074fcfa92e42f72f8cfc1a35eb2850ce9a610c3a6f34d393df2270b2917dbc6
+size 5240

config.json

@@ -0,0 +1,39 @@
+{
+  "_attn_implementation_autoset": true,
+  "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": "4.51.3",
+  "use_cache": false,
+  "vocab_size": 50257
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bbe11950022b53f8820e499a57bbaac87e217ba4682e1486ee79793f4d0329b
+size 1281583254

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6074fcfa92e42f72f8cfc1a35eb2850ce9a610c3a6f34d393df2270b2917dbc6
+size 5240