Upload folder using huggingface_hub

checkpoints/checkpoint-441/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-441/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-441/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e35d84287f5ba87e7965e76a4b5ee6e22a5a2d2cea0af6424d3f731c9966a81
+size 388979624

checkpoints/checkpoint-441/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6df60d81e3af37f71fc8ce87e7b18853dab1d49ed63c9ab019b99e872d06e985
+size 778027770

checkpoints/checkpoint-441/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c70a41264c08a1e8401b7173fe9901cfca41eb5cf987bd975ed722bcda9db818
+size 14244

checkpoints/checkpoint-441/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e42587ca5bdf0efaf291b0ec89a1993ff82fc7e1df71f0251a757792d4b2a620
+size 1064

checkpoints/checkpoint-441/trainer_state.json

@@ -0,0 +1,179 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.0,
+  "eval_steps": 500,
+  "global_step": 441,
+  "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": 7.2673492431640625,
+      "eval_normalizer": 682934.0,
+      "eval_runtime": 102.7425,
+      "eval_samples_per_second": 520.301,
+      "eval_steps_per_second": 1.022,
+      "step": 49
+    },
+    {
+      "epoch": 1.020460358056266,
+      "grad_norm": 18.3385066986084,
+      "learning_rate": 0.00011666666666666667,
+      "loss": 131.2483,
+      "step": 50
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.0,
+      "eval_loss": 6.509530067443848,
+      "eval_normalizer": 682934.0,
+      "eval_runtime": 102.5447,
+      "eval_samples_per_second": 521.304,
+      "eval_steps_per_second": 1.024,
+      "step": 98
+    },
+    {
+      "epoch": 2.040920716112532,
+      "grad_norm": 9.990983009338379,
+      "learning_rate": 0.00023333333333333333,
+      "loss": 97.4735,
+      "step": 100
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.0,
+      "eval_loss": 5.903900146484375,
+      "eval_normalizer": 682934.0,
+      "eval_runtime": 103.1873,
+      "eval_samples_per_second": 518.058,
+      "eval_steps_per_second": 1.018,
+      "step": 147
+    },
+    {
+      "epoch": 3.061381074168798,
+      "grad_norm": 10.024227142333984,
+      "learning_rate": 0.00035,
+      "loss": 82.2404,
+      "step": 150
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.0,
+      "eval_loss": 5.608065605163574,
+      "eval_normalizer": 682934.0,
+      "eval_runtime": 102.8393,
+      "eval_samples_per_second": 519.811,
+      "eval_steps_per_second": 1.021,
+      "step": 196
+    },
+    {
+      "epoch": 4.081841432225064,
+      "grad_norm": 8.950803756713867,
+      "learning_rate": 0.00046666666666666666,
+      "loss": 74.4832,
+      "step": 200
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.0,
+      "eval_loss": 5.360286235809326,
+      "eval_normalizer": 682934.0,
+      "eval_runtime": 144.9517,
+      "eval_samples_per_second": 368.792,
+      "eval_steps_per_second": 0.724,
+      "step": 245
+    },
+    {
+      "epoch": 5.10230179028133,
+      "grad_norm": 7.838677406311035,
+      "learning_rate": 0.0005833333333333334,
+      "loss": 69.0075,
+      "step": 250
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.0,
+      "eval_loss": 5.131760120391846,
+      "eval_normalizer": 682934.0,
+      "eval_runtime": 101.9406,
+      "eval_samples_per_second": 524.394,
+      "eval_steps_per_second": 1.03,
+      "step": 294
+    },
+    {
+      "epoch": 6.122762148337596,
+      "grad_norm": 8.561175346374512,
+      "learning_rate": 0.0007,
+      "loss": 64.0665,
+      "step": 300
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.0,
+      "eval_loss": 5.031791687011719,
+      "eval_normalizer": 682934.0,
+      "eval_runtime": 102.179,
+      "eval_samples_per_second": 523.17,
+      "eval_steps_per_second": 1.028,
+      "step": 343
+    },
+    {
+      "epoch": 7.143222506393862,
+      "grad_norm": 5.454161167144775,
+      "learning_rate": 0.0005749756633902887,
+      "loss": 59.5088,
+      "step": 350
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.0,
+      "eval_loss": 4.981640815734863,
+      "eval_normalizer": 682934.0,
+      "eval_runtime": 102.9651,
+      "eval_samples_per_second": 519.176,
+      "eval_steps_per_second": 1.02,
+      "step": 392
+    },
+    {
+      "epoch": 8.163682864450127,
+      "grad_norm": 5.067333221435547,
+      "learning_rate": 0.0002892231378165744,
+      "loss": 55.1264,
+      "step": 400
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.0,
+      "eval_loss": 5.057043552398682,
+      "eval_normalizer": 682934.0,
+      "eval_runtime": 103.0139,
+      "eval_samples_per_second": 518.93,
+      "eval_steps_per_second": 1.019,
+      "step": 441
+    }
+  ],
+  "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": 1.1886541273379635e+17,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/checkpoint-441/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38308b595d8f919553393c186494d3ec4d0a2be8d9da1d1cf7c4c64774c09ae6
+size 5432