Upload task output ca94f77a-b7f8-4dec-a8c2-6cb5c1f2aaf4

config.json

@@ -5,7 +5,6 @@
   "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 1,
-  "dtype": "float16",
   "eos_token_id": 2,
   "head_dim": 100,
   "hidden_act": "silu",
@@ -21,15 +20,11 @@
   "pad_token_id": 0,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-06,
-  "rope_parameters": {
-    "rope_theta": 10000.0,
-    "rope_type": "default"
-  },
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.51.3",
-  "use_cache": true,
+  "use_cache": false,
   "vocab_size": 32000
 }

generation_config.json

@@ -1,5 +1,7 @@
 {
-  "temperature": null,
-  "top_p": null,
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
   "transformers_version": "4.51.3"
 }

loss.txt

@@ -0,0 +1 @@
+8,1.1050758361816406

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3074e569bdc7f7cd79cc21f1718cdce22a6f6cbe9836fbfbb7770131a06a2ffa
+oid sha256:4dc2f039d3ddb20c9046f3bc7bb8b8ab3ad6576cb62fb3a6c7538204b77856ec
 size 4995335576

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52f2d1ac2c594644fb6e82f84eb383337d82f45baad0ebfdc5adec8b95a2fa84
+oid sha256:22c7911f79ae44b9255c63ecc485a46e60d6f00f5de6935168c2a0eea0eff526
 size 1857639032

special_tokens_map.json

@@ -13,6 +13,7 @@
     "rstrip": false,
     "single_word": false
   },
+  "pad_token": "</s>",
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer.json

@@ -31,13 +31,23 @@
       "special": true
     }
   ],
-  "normalizer": null,
-  "pre_tokenizer": {
-    "type": "Metaspace",
-    "replacement": "▁",
-    "prepend_scheme": "always",
-    "split": false
+  "normalizer": {
+    "type": "Sequence",
+    "normalizers": [
+      {
+        "type": "Prepend",
+        "prepend": "▁"
+      },
+      {
+        "type": "Replace",
+        "pattern": {
+          "String": " "
+        },
+        "content": "▁"
+      }
+    ]
   },
+  "pre_tokenizer": null,
   "post_processor": {
     "type": "TemplateProcessing",
     "single": [
@@ -119,7 +129,7 @@
   "model": {
     "type": "BPE",
     "dropout": null,
-    "unk_token": null,
+    "unk_token": "<unk>",
     "continuing_subword_prefix": null,
     "end_of_word_suffix": null,
     "fuse_unk": true,

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91b289e85fa20fd375d8b33dc12f77616f18abc6359804471d1fafcb425fecb8
+size 511574

tokenizer_config.json

@@ -28,18 +28,15 @@
       "special": true
     }
   },
-  "backend": "tokenizers",
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "extra_special_tokens": {},
-  "is_local": false,
   "legacy": true,
-  "local_files_only": false,
   "model_max_length": 2048,
-  "pad_token": null,
+  "pad_token": "</s>",
   "sp_model_kwargs": {},
-  "tokenizer_class": "LlamaTokenizerFast",
+  "tokenizer_class": "LlamaTokenizer",
   "unk_token": "<unk>",
   "use_default_system_prompt": false
 }

trainer_state.json

@@ -0,0 +1,57 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.6,
+  "eval_steps": 500,
+  "global_step": 8,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.8,
+      "eval_loss": 1.1666377782821655,
+      "eval_runtime": 6.6333,
+      "eval_samples_per_second": 29.246,
+      "eval_steps_per_second": 29.246,
+      "step": 4
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 11.4375,
+      "learning_rate": 1.812023303197022e-05,
+      "loss": 1.1071,
+      "step": 5
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 1.1050758361816406,
+      "eval_runtime": 6.4994,
+      "eval_samples_per_second": 29.849,
+      "eval_steps_per_second": 29.849,
+      "step": 8
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 50,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "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": 6923433679257600.0,
+  "train_batch_size": 48,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d56067b6e6fca3b6186fe3d38d7ce913a40598dcc758475f4efc97c1cdbbb2cc
+size 5688