Actualización del modelo checkpoint-6000

.ipynb_checkpoints/config-checkpoint.json

@@ -0,0 +1,32 @@
+{
+  "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,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.3",
+  "use_cache": true,
+  "vocab_size": 32000
+}

config.json

@@ -0,0 +1,32 @@
+{
+  "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,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.3",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.48.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:238ab42553be8fc3276610b67c07339429ab61e9b3f8f2b2d218aed3e4ca07a7
+size 441688704

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:576ae156a30975aea89972278d576665dce6fd9ed104db62242d985ba6444cf4
+size 883471290

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5345d70bc19018e998f69ac4b42c33f542673240cb13fd624a4131428322821
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abf4e8f15b919e4ad1922068bdbba1f948f1a02e34d004401a6af2ada11f889b
+size 1064

trainer_state.json

@@ -0,0 +1,117 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.09830425165888425,
+  "eval_steps": 500,
+  "global_step": 6000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008192020971573687,
+      "grad_norm": 0.2447698563337326,
+      "learning_rate": 0.0001494,
+      "loss": 2.4052,
+      "step": 500
+    },
+    {
+      "epoch": 0.016384041943147375,
+      "grad_norm": 0.29972031712532043,
+      "learning_rate": 0.00029939999999999996,
+      "loss": 1.8314,
+      "step": 1000
+    },
+    {
+      "epoch": 0.024576062914721062,
+      "grad_norm": 0.22787177562713623,
+      "learning_rate": 0.0004494,
+      "loss": 1.6945,
+      "step": 1500
+    },
+    {
+      "epoch": 0.03276808388629475,
+      "grad_norm": 0.21664758026599884,
+      "learning_rate": 0.0005993999999999999,
+      "loss": 1.5686,
+      "step": 2000
+    },
+    {
+      "epoch": 0.04096010485786843,
+      "grad_norm": 0.177582785487175,
+      "learning_rate": 0.0005998946571323422,
+      "loss": 1.4698,
+      "step": 2500
+    },
+    {
+      "epoch": 0.049152125829442124,
+      "grad_norm": 0.21073713898658752,
+      "learning_rate": 0.0005995770092517366,
+      "loss": 1.41,
+      "step": 3000
+    },
+    {
+      "epoch": 0.05734414680101581,
+      "grad_norm": 0.17612150311470032,
+      "learning_rate": 0.0005990472795339199,
+      "loss": 1.3714,
+      "step": 3500
+    },
+    {
+      "epoch": 0.0655361677725895,
+      "grad_norm": 0.17588965594768524,
+      "learning_rate": 0.0005983058429944914,
+      "loss": 1.3247,
+      "step": 4000
+    },
+    {
+      "epoch": 0.07372818874416319,
+      "grad_norm": 0.17322216928005219,
+      "learning_rate": 0.0005973532245242761,
+      "loss": 1.2806,
+      "step": 4500
+    },
+    {
+      "epoch": 0.08192020971573687,
+      "grad_norm": 0.1861853152513504,
+      "learning_rate": 0.0005961900985177338,
+      "loss": 1.279,
+      "step": 5000
+    },
+    {
+      "epoch": 0.09011223068731056,
+      "grad_norm": 0.14911051094532013,
+      "learning_rate": 0.0005948172883955301,
+      "loss": 1.2516,
+      "step": 5500
+    },
+    {
+      "epoch": 0.09830425165888425,
+      "grad_norm": 0.18009094893932343,
+      "learning_rate": 0.000593235766021606,
+      "loss": 1.2326,
+      "step": 6000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 61035,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9223372036854775807,
+  "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": 1.00336140288e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60212d31eadc60fa4b0a9bb3dc5e02e522ab09238a609235b299d38f3aef19fc
+size 5304