Upload task output 1

config.json

@@ -5,7 +5,6 @@
   "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 0,
-  "dtype": "bfloat16",
   "eos_token_id": 0,
   "head_dim": 64,
   "hidden_act": "silu",
@@ -18,15 +17,13 @@
   "num_attention_heads": 32,
   "num_hidden_layers": 24,
   "num_key_value_heads": 32,
-  "pad_token_id": 16,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
-  "rope_parameters": {
-    "rope_theta": 10000.0,
-    "rope_type": "default"
-  },
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
   "tie_word_embeddings": true,
-  "transformers_version": "5.5.3",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
   "use_cache": false,
   "vocab_size": 49152
 }

generation_config.json

@@ -1,9 +1,6 @@
 {
   "_from_model_config": true,
   "bos_token_id": 0,
-  "eos_token_id": [
-    0
-  ],
-  "pad_token_id": 16,
-  "transformers_version": "5.5.3"
+  "eos_token_id": 0,
+  "transformers_version": "4.51.3"
 }

loss.txt

@@ -1 +1 @@
-26,1.0655913352966309
+98,0.7979409694671631

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d33bec44db925d7c889b0bcfe82c7f38f34c6a07fc4560f7b4762d4aeca56da6
+oid sha256:7fb1e744cd64df5d292b188edcb2449bc683b75fe274e8f11e9258270e0e2498
 size 3422777952

special_tokens_map.json

@@ -0,0 +1,49 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|im_start|>",
+    "<|im_end|>",
+    "<repo_name>",
+    "<reponame>",
+    "<file_sep>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>"
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<empty_output>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -159,37 +159,21 @@
   ],
   "normalizer": null,
   "pre_tokenizer": {
-    "type": "ByteLevel",
-    "add_prefix_space": false,
-    "trim_offsets": true,
-    "use_regex": true
-  },
-  "post_processor": {
-    "type": "TemplateProcessing",
-    "single": [
+    "type": "Sequence",
+    "pretokenizers": [
       {
-        "Sequence": {
-          "id": "A",
-          "type_id": 0
-        }
-      }
-    ],
-    "pair": [
-      {
-        "Sequence": {
-          "id": "A",
-          "type_id": 0
-        }
+        "type": "Digits",
+        "individual_digits": true
       },
       {
-        "Sequence": {
-          "id": "B",
-          "type_id": 1
-        }
+        "type": "ByteLevel",
+        "add_prefix_space": false,
+        "trim_offsets": true,
+        "use_regex": true
       }
-    ],
-    "special_tokens": {}
+    ]
   },
+  "post_processor": null,
   "decoder": {
     "type": "ByteLevel",
     "add_prefix_space": true,
@@ -200,8 +184,8 @@
     "type": "BPE",
     "dropout": null,
     "unk_token": null,
-    "continuing_subword_prefix": "",
-    "end_of_word_suffix": "",
+    "continuing_subword_prefix": null,
+    "end_of_word_suffix": null,
     "fuse_unk": false,
     "byte_fallback": false,
     "ignore_merges": false,

tokenizer_config.json

@@ -1,11 +1,144 @@
 {
   "add_prefix_space": false,
-  "backend": "tokenizers",
-  "bos_token": "<|endoftext|>",
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<|endoftext|>",
-  "errors": "replace",
-  "extra_special_tokens": [
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<repo_name>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<file_sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<jupyter_script>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
     "<|endoftext|>",
     "<|im_start|>",
     "<|im_end|>",
@@ -24,7 +157,10 @@
     "<jupyter_script>",
     "<empty_output>"
   ],
-  "is_local": true,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<empty_output>",
   "padding_side": "left",

trainer_state.json

@@ -2,59 +2,165 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9629629629629629,
+  "epoch": 2.0,
   "eval_steps": 500,
-  "global_step": 26,
+  "global_step": 98,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.18518518518518517,
-      "grad_norm": 0.6171875,
-      "learning_rate": 0.00016374573805303646,
-      "loss": 1.3399703979492188,
+      "epoch": 0.10204081632653061,
+      "grad_norm": 0.68359375,
+      "learning_rate": 7.314242018863303e-05,
+      "loss": 1.3342,
       "step": 5
     },
     {
-      "epoch": 0.37037037037037035,
-      "grad_norm": 0.5546875,
-      "learning_rate": 0.000368427910619332,
-      "loss": 1.1718379020690919,
+      "epoch": 0.20408163265306123,
+      "grad_norm": 0.48046875,
+      "learning_rate": 0.0001645704454244243,
+      "loss": 1.217,
       "step": 10
     },
     {
-      "epoch": 0.5555555555555556,
-      "grad_norm": 0.48046875,
-      "learning_rate": 0.0005731100831856276,
-      "loss": 1.101071834564209,
+      "epoch": 0.30612244897959184,
+      "grad_norm": 0.427734375,
+      "learning_rate": 0.0002559984706602156,
+      "loss": 1.1263,
       "step": 15
     },
     {
-      "epoch": 0.7407407407407407,
-      "grad_norm": 0.419921875,
-      "learning_rate": 0.0007777922557519231,
-      "loss": 1.0388586044311523,
+      "epoch": 0.40816326530612246,
+      "grad_norm": 0.43359375,
+      "learning_rate": 0.0003474264958960069,
+      "loss": 1.0322,
       "step": 20
     },
     {
-      "epoch": 0.9259259259259259,
-      "grad_norm": 0.369140625,
-      "learning_rate": 0.0009824744283182187,
-      "loss": 1.0427934646606445,
+      "epoch": 0.5102040816326531,
+      "grad_norm": 0.326171875,
+      "learning_rate": 0.00043885452113179817,
+      "loss": 0.9784,
       "step": 25
     },
     {
-      "epoch": 0.9629629629629629,
-      "eval_loss": 1.0655913352966309,
-      "eval_runtime": 2.8604,
-      "eval_samples_per_second": 33.562,
-      "eval_steps_per_second": 33.562,
-      "step": 26
+      "epoch": 0.6122448979591837,
+      "grad_norm": 0.318359375,
+      "learning_rate": 0.0005302825463675895,
+      "loss": 0.954,
+      "step": 30
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 0.36328125,
+      "learning_rate": 0.0006217105716033808,
+      "loss": 0.9084,
+      "step": 35
+    },
+    {
+      "epoch": 0.8163265306122449,
+      "grad_norm": 0.341796875,
+      "learning_rate": 0.0006384871160400743,
+      "loss": 0.9099,
+      "step": 40
+    },
+    {
+      "epoch": 0.9183673469387755,
+      "grad_norm": 0.318359375,
+      "learning_rate": 0.0006323890674048986,
+      "loss": 0.8874,
+      "step": 45
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.9023501873016357,
+      "eval_runtime": 7.2343,
+      "eval_samples_per_second": 27.508,
+      "eval_steps_per_second": 27.508,
+      "step": 49
+    },
+    {
+      "epoch": 1.0204081632653061,
+      "grad_norm": 0.5703125,
+      "learning_rate": 0.0006217273735914285,
+      "loss": 0.8344,
+      "step": 50
+    },
+    {
+      "epoch": 1.1224489795918366,
+      "grad_norm": 0.294921875,
+      "learning_rate": 0.0006067114062701753,
+      "loss": 0.6302,
+      "step": 55
+    },
+    {
+      "epoch": 1.2244897959183674,
+      "grad_norm": 0.314453125,
+      "learning_rate": 0.0005876360452432976,
+      "loss": 0.6713,
+      "step": 60
+    },
+    {
+      "epoch": 1.3265306122448979,
+      "grad_norm": 0.322265625,
+      "learning_rate": 0.0005648758876689657,
+      "loss": 0.6466,
+      "step": 65
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 0.271484375,
+      "learning_rate": 0.0005388778918162697,
+      "loss": 0.6401,
+      "step": 70
+    },
+    {
+      "epoch": 1.5306122448979593,
+      "grad_norm": 0.30078125,
+      "learning_rate": 0.000510152599810772,
+      "loss": 0.6184,
+      "step": 75
+    },
+    {
+      "epoch": 1.6326530612244898,
+      "grad_norm": 0.333984375,
+      "learning_rate": 0.00047926411173622446,
+      "loss": 0.6219,
+      "step": 80
+    },
+    {
+      "epoch": 1.7346938775510203,
+      "grad_norm": 0.26171875,
+      "learning_rate": 0.0004468190079785287,
+      "loss": 0.5841,
+      "step": 85
+    },
+    {
+      "epoch": 1.836734693877551,
+      "grad_norm": 0.30078125,
+      "learning_rate": 0.0004134544373521701,
+      "loss": 0.6111,
+      "step": 90
+    },
+    {
+      "epoch": 1.9387755102040818,
+      "grad_norm": 0.29296875,
+      "learning_rate": 0.00037982560493151593,
+      "loss": 0.6008,
+      "step": 95
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.7979409694671631,
+      "eval_runtime": 7.2562,
+      "eval_samples_per_second": 27.425,
+      "eval_steps_per_second": 27.425,
+      "step": 98
     }
   ],
   "logging_steps": 5,
-  "max_steps": 81,
+  "max_steps": 147,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 500,
@@ -70,7 +176,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.28650875764736e+16,
+  "total_flos": 1.939659357683712e+17,
   "train_batch_size": 100,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cdbe344a458daecf00b4816bf77d92a2e79336e491ef61a90bd3a31c8f557aa
-size 5048
+oid sha256:b63145236afd054cdb24760dd8ff2b8fc8468f88f16b4d28eadcb2c2ea926a20
+size 5560