Upload folder using huggingface_hub

checkpoints/checkpoint-392/config.json

@@ -0,0 +1,30 @@
+{
+  "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": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "max_position_embeddings": 256,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "num_key_value_heads": 12,
+  "pad_token_id": 1,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0",
+  "use_cache": true,
+  "vocab_size": 16000
+}

checkpoints/checkpoint-392/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.47.0"
+}

checkpoints/checkpoint-392/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89dd2898e110e4b816f0ac9abecbaa2dcc64c1513f4b6abc40ed6ec18538efc3
+size 388979624

checkpoints/checkpoint-392/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb8b4825ccf5c878d103fd4c9691d8485cc697d3b651c975e007c7da6530115f
+size 778027770

checkpoints/checkpoint-392/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b38c7aeca1e87e48d8c036b2e49212373b3c77e08398771d2cb3c0516527df4d
+size 14244

checkpoints/checkpoint-392/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fc7695e6f3411cf97f4227c3e2d5dd244d5c9097f15decc22a18fd04aa8d1de
+size 1064

checkpoints/checkpoint-392/trainer_state.json

@@ -0,0 +1,162 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "global_step": 392,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.0,
+      "eval_loss": 8.68072509765625,
+      "eval_normalizer": 682934.0,
+      "eval_runtime": 103.8689,
+      "eval_samples_per_second": 514.658,
+      "eval_steps_per_second": 1.011,
+      "step": 49
+    },
+    {
+      "epoch": 1.020460358056266,
+      "grad_norm": 15.09317684173584,
+      "learning_rate": 0.00011666666666666667,
+      "loss": 122.1948,
+      "step": 50
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.0,
+      "eval_loss": 8.252920150756836,
+      "eval_normalizer": 682934.0,
+      "eval_runtime": 104.1996,
+      "eval_samples_per_second": 513.025,
+      "eval_steps_per_second": 1.008,
+      "step": 98
+    },
+    {
+      "epoch": 2.040920716112532,
+      "grad_norm": 213.40853881835938,
+      "learning_rate": 0.00023333333333333333,
+      "loss": 83.3595,
+      "step": 100
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.0,
+      "eval_loss": 6.694802761077881,
+      "eval_normalizer": 682934.0,
+      "eval_runtime": 103.6828,
+      "eval_samples_per_second": 515.582,
+      "eval_steps_per_second": 1.013,
+      "step": 147
+    },
+    {
+      "epoch": 3.061381074168798,
+      "grad_norm": 10.604432106018066,
+      "learning_rate": 0.00035,
+      "loss": 99.3263,
+      "step": 150
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.0,
+      "eval_loss": 6.354994297027588,
+      "eval_normalizer": 682934.0,
+      "eval_runtime": 109.9921,
+      "eval_samples_per_second": 486.008,
+      "eval_steps_per_second": 0.955,
+      "step": 196
+    },
+    {
+      "epoch": 4.081841432225064,
+      "grad_norm": 69.97613525390625,
+      "learning_rate": 0.00046666666666666666,
+      "loss": 81.0065,
+      "step": 200
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.0,
+      "eval_loss": 6.155397891998291,
+      "eval_normalizer": 682934.0,
+      "eval_runtime": 107.3605,
+      "eval_samples_per_second": 497.92,
+      "eval_steps_per_second": 0.978,
+      "step": 245
+    },
+    {
+      "epoch": 5.10230179028133,
+      "grad_norm": 5.2235107421875,
+      "learning_rate": 0.0005833333333333334,
+      "loss": 60.4213,
+      "step": 250
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.0,
+      "eval_loss": 6.170221328735352,
+      "eval_normalizer": 682934.0,
+      "eval_runtime": 107.8482,
+      "eval_samples_per_second": 495.669,
+      "eval_steps_per_second": 0.974,
+      "step": 294
+    },
+    {
+      "epoch": 6.122762148337596,
+      "grad_norm": 29.813343048095703,
+      "learning_rate": 0.0007,
+      "loss": 53.6331,
+      "step": 300
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.0,
+      "eval_loss": 5.645622253417969,
+      "eval_normalizer": 682934.0,
+      "eval_runtime": 107.7398,
+      "eval_samples_per_second": 496.168,
+      "eval_steps_per_second": 0.975,
+      "step": 343
+    },
+    {
+      "epoch": 7.143222506393862,
+      "grad_norm": 6.841020584106445,
+      "learning_rate": 0.0005749756633902887,
+      "loss": 67.0143,
+      "step": 350
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.0,
+      "eval_loss": 6.154343605041504,
+      "eval_normalizer": 682934.0,
+      "eval_runtime": 108.0173,
+      "eval_samples_per_second": 494.893,
+      "eval_steps_per_second": 0.972,
+      "step": 392
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 480,
+  "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": 8.926300917684634e+16,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/checkpoint-392/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac7e8db4932bb2458c24d940a9b9955f408bbe1709ac97dbe703e87d7ed899bf
+size 5432