Training Files Initial Commit

config.json

@@ -0,0 +1,23 @@
+{
+  "architectures": [
+    "LLaMAForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 2048,
+  "max_sequence_length": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "pad_token_id": -1,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.30.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ad5add92ee7ee82990a7f172c269e8196b546ad9a93ba55ef80f9ef4a62387f
+size 33661637

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:310d00ad54467c1b7503ed8f698a03db8bba710cfd20c331d1008c263be55ac8
+size 16822989

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d049cafb18b7f47a234fcf3866a4c2c804a164a31e8971d4e7c32238f9d7371
+size 14575

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a79944e2dfd765a29c7ec78561cfb25a4e79d7bdb4c76c3a8717188592da7b04
+size 557

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ecb7f65706cd916292a57e300dc43e4958eda7c3173cd4257f810ab135d1349
+size 627

trainer_state.json

@@ -0,0 +1,80 @@
+{
+  "best_metric": 2.451780080795288,
+  "best_model_checkpoint": "/content/Model/checkpoint-8",
+  "epoch": 0.12,
+  "global_step": 8,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 2.7323,
+      "step": 1
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.9999999999999995e-05,
+      "loss": 2.7914,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.999999999999999e-05,
+      "loss": 2.7974,
+      "step": 3
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00011999999999999999,
+      "loss": 2.7408,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "eval_loss": 2.6886792182922363,
+      "eval_runtime": 275.0654,
+      "eval_samples_per_second": 3.912,
+      "eval_steps_per_second": 0.491,
+      "step": 4
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00015,
+      "loss": 2.6641,
+      "step": 5
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00017999999999999998,
+      "loss": 2.604,
+      "step": 6
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00020999999999999998,
+      "loss": 2.5921,
+      "step": 7
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 2.5239,
+      "step": 8
+    },
+    {
+      "epoch": 0.12,
+      "eval_loss": 2.451780080795288,
+      "eval_runtime": 274.9467,
+      "eval_samples_per_second": 3.913,
+      "eval_steps_per_second": 0.491,
+      "step": 8
+    }
+  ],
+  "max_steps": 10,
+  "num_train_epochs": 1,
+  "total_flos": 1.0631008082460672e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:279014beb727af8f676d08c7607ed2bcce578a742f1dab4d834ec6848d07c9f8
+size 3899