Upload 10 files

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "/home/dousti_group/ghanizadeh/.cache/huggingface/hub/models--HuggingFaceTB--SmolLM-135M/snapshots/1d461723eec654e65efdc40cf49301c89c0c92f4",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "pad_token_id": 1,
+  "hidden_act": "silu",
+  "hidden_size": 576,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "max_position_embeddings": 128,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 9,
+  "num_hidden_layers": 30,
+  "num_key_value_heads": 3,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.43.4",
+  "use_cache": true,
+  "vocab_size": 30001
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.43.4"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46fbd23a84ca3df081c6cf84bb2b12a71cb1f51aea954c298768c5e2d95b203d
+size 493966464

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9899ccda7f0d8d9511991180b93aab508ce6e8489de708c88ad1188e7e1d90d6
+size 14244

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+    "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
+    }
+  }
+  

trainer_state.json

@@ -0,0 +1,93 @@
+{
+  "best_metric": 3.5722010135650635,
+  "best_model_checkpoint": "/home/dousti_group/ghanizadeh/babyLM/model-save/5-epoch-tv-tokenized/checkpoint-113408",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 113408,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 5.181252479553223,
+      "learning_rate": 4.014476851196376e-05,
+      "loss": 4.3405,
+      "step": 28352
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 3.8782432079315186,
+      "eval_runtime": 163.7675,
+      "eval_samples_per_second": 291.572,
+      "eval_steps_per_second": 36.448,
+      "step": 28352
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 4.64185094833374,
+      "learning_rate": 3.0112558402944925e-05,
+      "loss": 3.7749,
+      "step": 56704
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 3.6707634925842285,
+      "eval_runtime": 158.0831,
+      "eval_samples_per_second": 302.056,
+      "eval_steps_per_second": 37.759,
+      "step": 56704
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 6.706910610198975,
+      "learning_rate": 2.0081056208410027e-05,
+      "loss": 3.493,
+      "step": 85056
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 3.5801351070404053,
+      "eval_runtime": 158.2132,
+      "eval_samples_per_second": 301.808,
+      "eval_steps_per_second": 37.728,
+      "step": 85056
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 10.424848556518555,
+      "learning_rate": 1.005061588560102e-05,
+      "loss": 3.2244,
+      "step": 113408
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 3.5722010135650635,
+      "eval_runtime": 157.7259,
+      "eval_samples_per_second": 302.74,
+      "eval_steps_per_second": 37.844,
+      "step": 113408
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 141760,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "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": 2.959934159506637e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e748a7dd088443d1a66c1f4b06198ed9374d6718be69d7883b42f2fbb8df6281
+size 5304