Upload new model

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 32000
+}

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "outputs/checkpoint-808",
+  "_name_or_path": "outputs/checkpoint-1960",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -21,7 +21,7 @@
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.34.0",
+  "transformers_version": "4.34.1",
   "use_cache": true,
   "vocab_size": 32001
 }

generation_config.json

@@ -6,5 +6,5 @@
   "pad_token_id": 0,
   "temperature": 0.6,
   "top_p": 0.9,
-  "transformers_version": "4.34.0"
+  "transformers_version": "4.34.1"
 }

pytorch_model-00001-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de11e1eac25e346e42ff6cd66da9a9b234ce42d76b27076d3b1eca29adf06bab
+oid sha256:a5d5d4f4733a155c795fe325b94aa9b5c44ea92d8d21af94b79a49e4df3b96d2
 size 9976628314

pytorch_model-00002-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1b13c92a83acd990ae75b07b7a8e19532c81d3e873a7ad842d4fd96463786eb
+oid sha256:b6f83ffcea0dc63f67b272d10a6ce0be34f06bf9bf3ab08992a589b426ee3c79
 size 3500318979

special_tokens_map.json

@@ -1,9 +1,30 @@
 {
-  "additional_special_tokens": [
-    "[PAD]"
-  ],
-  "bos_token": "<s>",
-  "eos_token": "</s>",
-  "pad_token": "[PAD]",
-  "unk_token": "<unk>"
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer_config.json

@@ -35,9 +35,6 @@
       "special": true
     }
   },
-  "additional_special_tokens": [
-    "[PAD]"
-  ],
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
@@ -48,7 +45,6 @@
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
-  "tokenizer_file": null,
   "unk_token": "<unk>",
   "use_default_system_prompt": true
 }

trainer_state.json

@@ -1,242 +1,150 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.292993630573248,
+  "epoch": 8.963414634146341,
   "eval_steps": 100,
-  "global_step": 1616,
+  "global_step": 2205,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.64,
+      "epoch": 0.41,
       "learning_rate": 2e-05,
-      "loss": 1.1355,
+      "loss": 1.3987,
       "step": 100
     },
     {
-      "epoch": 0.64,
-      "eval_loss": 1.157366156578064,
-      "eval_runtime": 30.4555,
-      "eval_samples_per_second": 65.67,
-      "eval_steps_per_second": 1.051,
-      "step": 100
-    },
-    {
-      "epoch": 1.27,
+      "epoch": 0.81,
       "learning_rate": 2e-05,
-      "loss": 0.881,
+      "loss": 1.1878,
       "step": 200
     },
     {
-      "epoch": 1.27,
-      "eval_loss": 1.3262789249420166,
-      "eval_runtime": 29.1383,
-      "eval_samples_per_second": 68.638,
-      "eval_steps_per_second": 1.098,
-      "step": 200
-    },
-    {
-      "epoch": 1.91,
+      "epoch": 1.22,
       "learning_rate": 2e-05,
-      "loss": 0.5496,
+      "loss": 0.7575,
       "step": 300
     },
     {
-      "epoch": 1.91,
-      "eval_loss": 1.3176809549331665,
-      "eval_runtime": 28.8909,
-      "eval_samples_per_second": 69.226,
-      "eval_steps_per_second": 1.108,
-      "step": 300
-    },
-    {
-      "epoch": 2.55,
+      "epoch": 1.63,
       "learning_rate": 2e-05,
-      "loss": 0.2597,
-      "step": 400
-    },
-    {
-      "epoch": 2.55,
-      "eval_loss": 1.5806535482406616,
-      "eval_runtime": 29.1193,
-      "eval_samples_per_second": 68.683,
-      "eval_steps_per_second": 1.099,
+      "loss": 0.7709,
       "step": 400
     },
     {
-      "epoch": 3.18,
+      "epoch": 2.03,
       "learning_rate": 2e-05,
-      "loss": 0.1877,
-      "step": 500
-    },
-    {
-      "epoch": 3.18,
-      "eval_loss": 1.7526657581329346,
-      "eval_runtime": 29.1196,
-      "eval_samples_per_second": 68.682,
-      "eval_steps_per_second": 1.099,
+      "loss": 0.3723,
       "step": 500
     },
     {
-      "epoch": 3.82,
+      "epoch": 2.44,
       "learning_rate": 2e-05,
-      "loss": 0.1158,
+      "loss": 0.3363,
       "step": 600
     },
     {
-      "epoch": 3.82,
-      "eval_loss": 1.7486767768859863,
-      "eval_runtime": 29.2706,
-      "eval_samples_per_second": 68.328,
-      "eval_steps_per_second": 1.093,
-      "step": 600
-    },
-    {
-      "epoch": 4.46,
+      "epoch": 2.85,
       "learning_rate": 2e-05,
-      "loss": 0.0855,
+      "loss": 0.3537,
       "step": 700
     },
     {
-      "epoch": 4.46,
-      "eval_loss": 1.873838186264038,
-      "eval_runtime": 29.2292,
-      "eval_samples_per_second": 68.425,
-      "eval_steps_per_second": 1.095,
-      "step": 700
-    },
-    {
-      "epoch": 5.1,
+      "epoch": 3.25,
       "learning_rate": 2e-05,
-      "loss": 0.0645,
-      "step": 800
-    },
-    {
-      "epoch": 5.1,
-      "eval_loss": 1.9275007247924805,
-      "eval_runtime": 29.013,
-      "eval_samples_per_second": 68.935,
-      "eval_steps_per_second": 1.103,
+      "loss": 0.1487,
       "step": 800
     },
     {
-      "epoch": 5.73,
+      "epoch": 3.66,
       "learning_rate": 2e-05,
-      "loss": 0.0518,
-      "step": 900
-    },
-    {
-      "epoch": 5.73,
-      "eval_loss": 1.9070993661880493,
-      "eval_runtime": 30.5536,
-      "eval_samples_per_second": 65.459,
-      "eval_steps_per_second": 1.047,
+      "loss": 0.1769,
       "step": 900
     },
     {
-      "epoch": 6.37,
+      "epoch": 4.07,
       "learning_rate": 2e-05,
-      "loss": 0.0464,
-      "step": 1000
-    },
-    {
-      "epoch": 6.37,
-      "eval_loss": 1.9601927995681763,
-      "eval_runtime": 28.9827,
-      "eval_samples_per_second": 69.007,
-      "eval_steps_per_second": 1.104,
+      "loss": 0.112,
       "step": 1000
     },
     {
-      "epoch": 7.01,
+      "epoch": 4.47,
       "learning_rate": 2e-05,
-      "loss": 0.0367,
+      "loss": 0.1087,
       "step": 1100
     },
     {
-      "epoch": 7.01,
-      "eval_loss": 1.973179817199707,
-      "eval_runtime": 29.0672,
-      "eval_samples_per_second": 68.806,
-      "eval_steps_per_second": 1.101,
-      "step": 1100
+      "epoch": 4.88,
+      "learning_rate": 2e-05,
+      "loss": 0.134,
+      "step": 1200
     },
     {
-      "epoch": 7.64,
+      "epoch": 5.28,
       "learning_rate": 2e-05,
-      "loss": 0.0288,
-      "step": 1200
+      "loss": 0.0765,
+      "step": 1300
     },
     {
-      "epoch": 7.64,
-      "eval_loss": 2.0399632453918457,
-      "eval_runtime": 29.0049,
-      "eval_samples_per_second": 68.954,
-      "eval_steps_per_second": 1.103,
-      "step": 1200
+      "epoch": 5.69,
+      "learning_rate": 2e-05,
+      "loss": 0.1008,
+      "step": 1400
     },
     {
-      "epoch": 8.28,
+      "epoch": 6.1,
       "learning_rate": 2e-05,
-      "loss": 0.0265,
-      "step": 1300
+      "loss": 0.1036,
+      "step": 1500
     },
     {
-      "epoch": 8.28,
-      "eval_loss": 2.0276734828948975,
-      "eval_runtime": 28.9115,
-      "eval_samples_per_second": 69.177,
-      "eval_steps_per_second": 1.107,
-      "step": 1300
+      "epoch": 6.5,
+      "learning_rate": 2e-05,
+      "loss": 0.0787,
+      "step": 1600
     },
     {
-      "epoch": 8.92,
+      "epoch": 6.91,
       "learning_rate": 2e-05,
-      "loss": 0.0287,
-      "step": 1400
+      "loss": 0.0881,
+      "step": 1700
     },
     {
-      "epoch": 8.92,
-      "eval_loss": 2.049071788787842,
-      "eval_runtime": 29.0231,
-      "eval_samples_per_second": 68.911,
-      "eval_steps_per_second": 1.103,
-      "step": 1400
+      "epoch": 7.32,
+      "learning_rate": 2e-05,
+      "loss": 0.0721,
+      "step": 1800
     },
     {
-      "epoch": 9.55,
+      "epoch": 7.72,
       "learning_rate": 2e-05,
-      "loss": 0.0195,
-      "step": 1500
+      "loss": 0.0671,
+      "step": 1900
     },
     {
-      "epoch": 9.55,
-      "eval_loss": 2.043515205383301,
-      "eval_runtime": 29.1891,
-      "eval_samples_per_second": 68.519,
-      "eval_steps_per_second": 1.096,
-      "step": 1500
+      "epoch": 8.13,
+      "learning_rate": 2e-05,
+      "loss": 0.0551,
+      "step": 2000
     },
     {
-      "epoch": 10.19,
+      "epoch": 8.54,
       "learning_rate": 2e-05,
-      "loss": 0.0215,
-      "step": 1600
+      "loss": 0.0654,
+      "step": 2100
     },
     {
-      "epoch": 10.19,
-      "eval_loss": 2.101804733276367,
-      "eval_runtime": 28.9478,
-      "eval_samples_per_second": 69.09,
-      "eval_steps_per_second": 1.105,
-      "step": 1600
+      "epoch": 8.94,
+      "learning_rate": 2e-05,
+      "loss": 0.0747,
+      "step": 2200
     }
   ],
   "logging_steps": 100,
-  "max_steps": 1616,
-  "num_train_epochs": 11,
-  "save_steps": 808,
+  "max_steps": 2205,
+  "num_train_epochs": 9,
+  "save_steps": 245,
   "total_flos": 0.0,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c542b075d6cb9ea197a0a9c5bf12a21814b6b9c336def7a2a6e041ffceb5612
-size 6715
+oid sha256:bc185baba748b6f040311f7d8ec8004bd4ae30f3802fbb54461bd7b4e96b9175
+size 6779