Upload folder using huggingface_hub

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "models/final_model",
+  "_name_or_path": "baiges/CatGPT",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -28,7 +28,7 @@
   "summary_type": "cls_index",
   "summary_use_proj": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.42.3",
+  "transformers_version": "4.44.2",
   "use_cache": true,
   "vocab_size": 32768
 }

generation_config.json

@@ -3,5 +3,5 @@
   "bos_token_id": 0,
   "eos_token_id": 2,
   "pad_token_id": 1,
-  "transformers_version": "4.42.3"
+  "transformers_version": "4.44.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aca488b3a34599938d4d60881ed94d9bdd771e69ee9e14445f200ce4f813967b
+oid sha256:352404be1b1166d0f819ba0bfde674390992da31c000d1f3ad7e3f684eaa1658
 size 444048000

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e2fdbbf2a7754074af730de9089f98ee7fb463665aca8d7ffa22b4cdc4bd0c7
+size 888189882

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8532a4b700094891bee71a4cd5621c15b04da2f3e774119925cac6e29b195ab
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c95a339ccdee60c82ce6d430ae6160c74f81f6a8f27cde3b69029269054f566c
+size 1064

trainer_state.json

@@ -0,0 +1,153 @@
+{
+  "best_metric": 1.3409229516983032,
+  "best_model_checkpoint": "results/checkpoint-2000",
+  "epoch": 1.4553392759687103,
+  "eval_steps": 250,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.18191740949608878,
+      "grad_norm": 0.2860318124294281,
+      "learning_rate": 2.976310216494586e-05,
+      "loss": 1.4647,
+      "step": 250
+    },
+    {
+      "epoch": 0.18191740949608878,
+      "eval_loss": 1.352885127067566,
+      "eval_runtime": 13.6056,
+      "eval_samples_per_second": 163.241,
+      "eval_steps_per_second": 20.433,
+      "step": 250
+    },
+    {
+      "epoch": 0.36383481899217757,
+      "grad_norm": 0.2909524440765381,
+      "learning_rate": 2.8342402320213494e-05,
+      "loss": 1.4643,
+      "step": 500
+    },
+    {
+      "epoch": 0.36383481899217757,
+      "eval_loss": 1.3520773649215698,
+      "eval_runtime": 13.6233,
+      "eval_samples_per_second": 163.029,
+      "eval_steps_per_second": 20.406,
+      "step": 500
+    },
+    {
+      "epoch": 0.5457522284882663,
+      "grad_norm": 0.2827763557434082,
+      "learning_rate": 2.5756526053283042e-05,
+      "loss": 1.4622,
+      "step": 750
+    },
+    {
+      "epoch": 0.5457522284882663,
+      "eval_loss": 1.350306749343872,
+      "eval_runtime": 13.6314,
+      "eval_samples_per_second": 162.932,
+      "eval_steps_per_second": 20.394,
+      "step": 750
+    },
+    {
+      "epoch": 0.7276696379843551,
+      "grad_norm": 0.29242751002311707,
+      "learning_rate": 2.223129492047081e-05,
+      "loss": 1.4625,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7276696379843551,
+      "eval_loss": 1.3474653959274292,
+      "eval_runtime": 13.6357,
+      "eval_samples_per_second": 162.882,
+      "eval_steps_per_second": 20.388,
+      "step": 1000
+    },
+    {
+      "epoch": 0.9095870474804438,
+      "grad_norm": 0.2826482653617859,
+      "learning_rate": 1.8074563242173716e-05,
+      "loss": 1.4591,
+      "step": 1250
+    },
+    {
+      "epoch": 0.9095870474804438,
+      "eval_loss": 1.3454625606536865,
+      "eval_runtime": 13.6252,
+      "eval_samples_per_second": 163.006,
+      "eval_steps_per_second": 20.403,
+      "step": 1250
+    },
+    {
+      "epoch": 1.0915044569765326,
+      "grad_norm": 0.28281259536743164,
+      "learning_rate": 1.3649333544377501e-05,
+      "loss": 1.4496,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0915044569765326,
+      "eval_loss": 1.3437364101409912,
+      "eval_runtime": 13.6378,
+      "eval_samples_per_second": 162.856,
+      "eval_steps_per_second": 20.384,
+      "step": 1500
+    },
+    {
+      "epoch": 1.2734218664726216,
+      "grad_norm": 0.2805255651473999,
+      "learning_rate": 9.34205597173652e-06,
+      "loss": 1.4453,
+      "step": 1750
+    },
+    {
+      "epoch": 1.2734218664726216,
+      "eval_loss": 1.3426544666290283,
+      "eval_runtime": 13.6433,
+      "eval_samples_per_second": 162.791,
+      "eval_steps_per_second": 20.376,
+      "step": 1750
+    },
+    {
+      "epoch": 1.4553392759687103,
+      "grad_norm": 0.2710939645767212,
+      "learning_rate": 5.528880047481714e-06,
+      "loss": 1.4438,
+      "step": 2000
+    },
+    {
+      "epoch": 1.4553392759687103,
+      "eval_loss": 1.3409229516983032,
+      "eval_runtime": 13.6488,
+      "eval_samples_per_second": 162.725,
+      "eval_steps_per_second": 20.368,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 250,
+  "max_steps": 2748,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "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": 1.67219584303104e+17,
+  "train_batch_size": 40,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e37234b8c597153081cceecae088e34e3af06badf790f270f4f82ad98044cdda
+size 5112