Training in progress, step 750

FINAL/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "C:/WorkingFolder/Models/SmolLM2-360M-Instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 960,
+  "initializer_range": 0.02,
+  "intermediate_size": 2560,
+  "is_llama_config": true,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 15,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 5,
+  "pad_token_id": 2,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_interleaved": false,
+  "rope_scaling": null,
+  "rope_theta": 100000,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers.js_config": {
+    "kv_cache_dtype": {
+      "fp16": "float16",
+      "q4f16": "float16"
+    }
+  },
+  "transformers_version": "4.48.1",
+  "use_cache": true,
+  "vocab_size": 49152
+}

FINAL/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 2,
+  "transformers_version": "4.48.1"
+}

FINAL/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41760a90a2f12db6955c9b6a958e2428eff6b2b4b3b5159326ec44776d3e8c60
+size 1447317080

FINAL/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b20f88730edeff159d4438cc3a6339110ff43cfd9b331e1e75f2089a76738772
+size 2894813306

FINAL/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a5b5e911d73b506345e399f41700d2610af622150ae128a8d07653de423dec7
+size 14244

FINAL/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fa496f3096e15ab6988b979b33587900f785adecdfb54ad9acaccd121f81f18
+size 1064

FINAL/special_tokens_map.json

@@ -0,0 +1,28 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": "<|im_start|>",
+  "eos_token": "<|im_end|>",
+  "pad_token": "<|im_end|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

FINAL/tokenizer_config.json

@@ -0,0 +1,155 @@
+{
+  "add_prefix_space": false,
+  "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": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<|im_start|>",
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": {},
+  "model_max_length": 8192,
+  "pad_token": "<|im_end|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

FINAL/trainer_state.json

@@ -0,0 +1,72 @@
+{
+  "best_metric": 1.8574875593185425,
+  "best_model_checkpoint": "C:/WorkingFolder/Models/ValA4\\checkpoint-500",
+  "epoch": 2.9874055415617127,
+  "eval_steps": 250,
+  "global_step": 594,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.256926952141058,
+      "grad_norm": 1.311490774154663,
+      "learning_rate": 2.8956228956228958e-05,
+      "loss": 2.0615,
+      "step": 250
+    },
+    {
+      "epoch": 1.256926952141058,
+      "eval_loss": 1.9107320308685303,
+      "eval_runtime": 19.178,
+      "eval_samples_per_second": 20.701,
+      "eval_steps_per_second": 2.607,
+      "step": 250
+    },
+    {
+      "epoch": 2.513853904282116,
+      "grad_norm": 1.4435200691223145,
+      "learning_rate": 7.912457912457913e-06,
+      "loss": 1.6447,
+      "step": 500
+    },
+    {
+      "epoch": 2.513853904282116,
+      "eval_loss": 1.8574875593185425,
+      "eval_runtime": 19.1861,
+      "eval_samples_per_second": 20.692,
+      "eval_steps_per_second": 2.606,
+      "step": 500
+    }
+  ],
+  "logging_steps": 250,
+  "max_steps": 594,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 250,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 2,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4583424363724800.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

FINAL/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96e821fbdce62b2cf729414cb53dc915d71723d51025888c81c5bb89c020860c
+size 5624

config.json

@@ -1,39 +1 @@
-{
-  "_name_or_path": "C:/WorkingFolder/Models/SmolLM2-360M-Instruct",
-  "architectures": [
-    "LlamaForCausalLM"
-  ],
-  "attention_bias": false,
-  "attention_dropout": 0.0,
-  "bos_token_id": 1,
-  "eos_token_id": 2,
-  "head_dim": 64,
-  "hidden_act": "silu",
-  "hidden_size": 960,
-  "initializer_range": 0.02,
-  "intermediate_size": 2560,
-  "is_llama_config": true,
-  "max_position_embeddings": 8192,
-  "mlp_bias": false,
-  "model_type": "llama",
-  "num_attention_heads": 15,
-  "num_hidden_layers": 32,
-  "num_key_value_heads": 5,
-  "pad_token_id": 2,
-  "pretraining_tp": 1,
-  "rms_norm_eps": 1e-05,
-  "rope_interleaved": false,
-  "rope_scaling": null,
-  "rope_theta": 100000,
-  "tie_word_embeddings": true,
-  "torch_dtype": "float32",
-  "transformers.js_config": {
-    "kv_cache_dtype": {
-      "fp16": "float16",
-      "q4f16": "float16"
-    }
-  },
-  "transformers_version": "4.48.1",
-  "use_cache": true,
-  "vocab_size": 49152
-}
+{"current_model": "checkpoint-750"}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad186577f63fcfac3b18bb5c864ebf5b11873d9ef7d9af20975b8e102bbf3852
+oid sha256:1563e954d4bc7dd94e3066d40f240b9c23b0b4c3e5649c1836a9a7428ae356fe
 size 1447317080

runs/Mar14_17-06-20_DESKTOP-LUSFFOR/events.out.tfevents.1741932382.DESKTOP-LUSFFOR.27012.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8ba0a064dfe08859ca9d8dea814a4efbe44109cd3200340a3f5892919c7b5db
-size 6188
+oid sha256:2c2eb1949f5f6968f3f8b8b737ba09cd7f4581f3f6588f8534d77424a8dfd3a3
+size 7024

runs/Mar15_04-31-09_DESKTOP-LUSFFOR/events.out.tfevents.1741973482.DESKTOP-LUSFFOR.27012.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc6a0d35be93dba188090ddad3465c7054cb3234332a95d031d25bf2b9e5ce5f
+size 6171

tokenizer.json

@@ -1,7 +1,21 @@
 {
   "version": "1.0",
-  "truncation": null,
-  "padding": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 512,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
+  "padding": {
+    "strategy": {
+      "Fixed": 512
+    },
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 2,
+    "pad_type_id": 0,
+    "pad_token": "<|im_end|>"
+  },
   "added_tokens": [
     {
       "id": 0,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96e821fbdce62b2cf729414cb53dc915d71723d51025888c81c5bb89c020860c
+oid sha256:7c41f8c034b567e9a900851aed9396a2edf29e71c5febe7dad09970f2262a175
 size 5624