Upload 14 files

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<Thought>": 50257
+}

config.json

@@ -5,6 +5,7 @@
   ],
   "attn_pdrop": 0.1,
   "bos_token_id": 1,
+  "dtype": "float32",
   "embd_pdrop": 0.1,
   "eos_token_id": 2,
   "gradient_checkpointing": false,
@@ -33,8 +34,7 @@
   "summary_proj_to_labels": true,
   "summary_type": "cls_index",
   "summary_use_proj": true,
-  "torch_dtype": "float32",
-  "transformers_version": "4.51.3",
+  "transformers_version": "4.57.0",
   "use_cache": true,
-  "vocab_size": 50264
+  "vocab_size": 50258
 }

generation_config.json

@@ -1,7 +1,9 @@
 {
   "_from_model_config": true,
   "bos_token_id": 1,
-  "eos_token_id": 2,
+  "eos_token_id": [
+    2
+  ],
   "pad_token_id": 0,
-  "transformers_version": "4.51.3"
+  "transformers_version": "4.57.0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b933eb783a99e61bb56c7166eb048e9e32ea03e570343980e5ffecb5dba32777
-size 500941440
+oid sha256:d613e790cd7b996c586bd592a1629fd2523962a8d41b2d59811d21a00a02b19d
+size 500923008

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18da2c9155cd816360d678fb26f921486eac0d676d4bdfa7ee845ae774c8febe
-size 1001976762
+oid sha256:d5e8fb28ca2b025604a8bb6a0183839d986906f09aa51aae586a61d54bbaa4b2
+size 1001942411

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d20fef646b31bd0da60e042930355f95bad6e9309ba53f239d47962584cee4ee
-size 14244
+oid sha256:68a252ed94a395c93ad12e059a0201f53477ef2c6cb571266a3603711265a034
+size 14645

scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a9acc78a1984093d893ebbe2aa3e8c676c849c54208c1237140b3e76d9d7d85
-size 988
+oid sha256:aaf72c95e5f10009a800f90c81f3898ad133ba4e6267316f252e283ab34c4c0e
+size 1383

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77d7bffa60dee30450bbde43b505ba5d1aeb72b9b39eb756f6197faaaea51f34
-size 1064
+oid sha256:b62a1567c6b47404cf0850ec3dd85b4092d190c27f4f873664e4a739a1a79063
+size 1465

special_tokens_map.json

@@ -0,0 +1,46 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<Thought>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,71 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "<Thought>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<Thought>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 2048,
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "tokenizer_class": "GPT2Tokenizer",
+  "truncation_side": "left",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_fast": true
+}

trainer_state.json

@@ -2,159 +2,82 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.088139281828074,
+  "epoch": 3.0,
   "eval_steps": 500,
-  "global_step": 2000,
+  "global_step": 939,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.0544069640914037,
-      "grad_norm": 1.3827155828475952,
-      "learning_rate": 4.913855640188611e-05,
-      "loss": 2.226,
+      "epoch": 0.32,
+      "grad_norm": 0.8309588432312012,
+      "learning_rate": 4.472843450479233e-05,
+      "loss": 2.1268,
       "step": 100
     },
     {
-      "epoch": 0.1088139281828074,
-      "grad_norm": 0.7897017002105713,
-      "learning_rate": 4.823177366702939e-05,
-      "loss": 1.2196,
+      "epoch": 0.64,
+      "grad_norm": 0.8111929893493652,
+      "learning_rate": 3.940362087326944e-05,
+      "loss": 1.9513,
       "step": 200
     },
     {
-      "epoch": 0.1632208922742111,
-      "grad_norm": 1.1451177597045898,
-      "learning_rate": 4.732499093217265e-05,
-      "loss": 1.2182,
+      "epoch": 0.96,
+      "grad_norm": 0.7366995215415955,
+      "learning_rate": 3.407880724174654e-05,
+      "loss": 1.9131,
       "step": 300
     },
     {
-      "epoch": 0.2176278563656148,
-      "grad_norm": 1.9186509847640991,
-      "learning_rate": 4.641820819731593e-05,
-      "loss": 1.2724,
+      "epoch": 1.2784,
+      "grad_norm": 0.7454879283905029,
+      "learning_rate": 2.8753993610223644e-05,
+      "loss": 1.8164,
       "step": 400
     },
     {
-      "epoch": 0.2720348204570185,
-      "grad_norm": 1.4905147552490234,
-      "learning_rate": 4.5511425462459194e-05,
-      "loss": 1.1771,
+      "epoch": 1.5984,
+      "grad_norm": 0.7343336939811707,
+      "learning_rate": 2.3429179978700748e-05,
+      "loss": 1.816,
       "step": 500
     },
     {
-      "epoch": 0.3264417845484222,
-      "grad_norm": 1.3085367679595947,
-      "learning_rate": 4.460464272760247e-05,
-      "loss": 1.1407,
+      "epoch": 1.9184,
+      "grad_norm": 0.7088562250137329,
+      "learning_rate": 1.8104366347177852e-05,
+      "loss": 1.7918,
       "step": 600
     },
     {
-      "epoch": 0.3808487486398259,
-      "grad_norm": 1.6310745477676392,
-      "learning_rate": 4.3697859992745737e-05,
-      "loss": 1.1146,
+      "epoch": 2.2368,
+      "grad_norm": 0.7369393706321716,
+      "learning_rate": 1.2779552715654951e-05,
+      "loss": 1.7424,
       "step": 700
     },
     {
-      "epoch": 0.4352557127312296,
-      "grad_norm": 1.0869531631469727,
-      "learning_rate": 4.2791077257889015e-05,
-      "loss": 1.1015,
+      "epoch": 2.5568,
+      "grad_norm": 0.7260516285896301,
+      "learning_rate": 7.4547390841320565e-06,
+      "loss": 1.744,
       "step": 800
     },
     {
-      "epoch": 0.4896626768226333,
-      "grad_norm": 1.387512445449829,
-      "learning_rate": 4.1884294523032286e-05,
-      "loss": 1.0764,
+      "epoch": 2.8768000000000002,
+      "grad_norm": 0.6936702728271484,
+      "learning_rate": 2.1299254526091587e-06,
+      "loss": 1.7355,
       "step": 900
-    },
-    {
-      "epoch": 0.544069640914037,
-      "grad_norm": 1.8865373134613037,
-      "learning_rate": 4.097751178817556e-05,
-      "loss": 1.079,
-      "step": 1000
-    },
-    {
-      "epoch": 0.5984766050054406,
-      "grad_norm": 1.1464284658432007,
-      "learning_rate": 4.007072905331883e-05,
-      "loss": 1.1797,
-      "step": 1100
-    },
-    {
-      "epoch": 0.6528835690968444,
-      "grad_norm": 1.3149100542068481,
-      "learning_rate": 3.91639463184621e-05,
-      "loss": 1.0676,
-      "step": 1200
-    },
-    {
-      "epoch": 0.7072905331882481,
-      "grad_norm": 1.3868759870529175,
-      "learning_rate": 3.825716358360537e-05,
-      "loss": 1.1711,
-      "step": 1300
-    },
-    {
-      "epoch": 0.7616974972796517,
-      "grad_norm": 1.046326994895935,
-      "learning_rate": 3.735038084874864e-05,
-      "loss": 1.1291,
-      "step": 1400
-    },
-    {
-      "epoch": 0.8161044613710555,
-      "grad_norm": 0.825319230556488,
-      "learning_rate": 3.6443598113891914e-05,
-      "loss": 1.0609,
-      "step": 1500
-    },
-    {
-      "epoch": 0.8705114254624592,
-      "grad_norm": 1.6592735052108765,
-      "learning_rate": 3.5536815379035185e-05,
-      "loss": 1.0676,
-      "step": 1600
-    },
-    {
-      "epoch": 0.9249183895538629,
-      "grad_norm": 1.2844988107681274,
-      "learning_rate": 3.4630032644178456e-05,
-      "loss": 1.062,
-      "step": 1700
-    },
-    {
-      "epoch": 0.9793253536452666,
-      "grad_norm": 1.3953850269317627,
-      "learning_rate": 3.372324990932173e-05,
-      "loss": 1.0538,
-      "step": 1800
-    },
-    {
-      "epoch": 1.0337323177366704,
-      "grad_norm": 1.2760506868362427,
-      "learning_rate": 3.2816467174465e-05,
-      "loss": 0.968,
-      "step": 1900
-    },
-    {
-      "epoch": 1.088139281828074,
-      "grad_norm": 1.5799071788787842,
-      "learning_rate": 3.190968443960827e-05,
-      "loss": 0.9365,
-      "step": 2000
     }
   ],
   "logging_steps": 100,
-  "max_steps": 5514,
+  "max_steps": 939,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
-  "save_steps": 500,
+  "save_steps": 5000,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -162,12 +85,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2090336256000000.0,
+  "total_flos": 7838760960000000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3b92fad9c09a73aae21441d2f394f747f6e1203d0cca82e74f610a1fc8e8dd1
-size 5304
+oid sha256:247d11e1712ddd52718707e0c098c161c131deb0e10e431622dcb2919154098c
+size 5777