Upload folder using huggingface_hub

checkpoints/checkpoint-522/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-522/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-522/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0136100cdc5743a1efb4b81212b0304a397e2d4c49954292f626acc1d3c6caa3
+size 388979624

checkpoints/checkpoint-522/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:363b52ee443c1b3d52545e15ee0ce603a5cdbf37c0e7f2e4dd6ca07216cd8afc
+size 778027770

checkpoints/checkpoint-522/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbd639ed55d4f78e0281de5f3620aa56e2f782e30d5a2defcb719b3b3c59b41a
+size 14244

checkpoints/checkpoint-522/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d8f3a307eed22f1313df190c7f6c8a82060004337e39fd7121f987e3c17faf8
+size 1064

checkpoints/checkpoint-522/trainer_state.json

@@ -0,0 +1,113 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9988041138483617,
+  "eval_steps": 500,
+  "global_step": 522,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09567089213106912,
+      "grad_norm": 19.851242065429688,
+      "learning_rate": 0.00011666666666666667,
+      "loss": 121.1525,
+      "step": 50
+    },
+    {
+      "epoch": 0.19134178426213824,
+      "grad_norm": 13.892197608947754,
+      "learning_rate": 0.00023333333333333333,
+      "loss": 77.1477,
+      "step": 100
+    },
+    {
+      "epoch": 0.2870126763932074,
+      "grad_norm": 12.60777759552002,
+      "learning_rate": 0.00035,
+      "loss": 64.8839,
+      "step": 150
+    },
+    {
+      "epoch": 0.3826835685242765,
+      "grad_norm": 8.890196800231934,
+      "learning_rate": 0.00046666666666666666,
+      "loss": 59.8849,
+      "step": 200
+    },
+    {
+      "epoch": 0.4783544606553456,
+      "grad_norm": 8.705379486083984,
+      "learning_rate": 0.0005833333333333334,
+      "loss": 57.5299,
+      "step": 250
+    },
+    {
+      "epoch": 0.5740253527864148,
+      "grad_norm": 7.457199573516846,
+      "learning_rate": 0.0007,
+      "loss": 56.2806,
+      "step": 300
+    },
+    {
+      "epoch": 0.6696962449174838,
+      "grad_norm": 7.943981647491455,
+      "learning_rate": 0.000699821634561209,
+      "loss": 55.3251,
+      "step": 350
+    },
+    {
+      "epoch": 0.765367137048553,
+      "grad_norm": 7.716305732727051,
+      "learning_rate": 0.0006992867200404345,
+      "loss": 52.4636,
+      "step": 400
+    },
+    {
+      "epoch": 0.8610380291796221,
+      "grad_norm": 7.123641014099121,
+      "learning_rate": 0.0006983958016391807,
+      "loss": 52.215,
+      "step": 450
+    },
+    {
+      "epoch": 0.9567089213106912,
+      "grad_norm": 7.223691463470459,
+      "learning_rate": 0.0006971497874091708,
+      "loss": 52.1157,
+      "step": 500
+    },
+    {
+      "epoch": 0.9988041138483617,
+      "eval_accuracy": 0.0,
+      "eval_loss": 8.116789817810059,
+      "eval_normalizer": 685885.0,
+      "eval_runtime": 103.9352,
+      "eval_samples_per_second": 514.33,
+      "eval_steps_per_second": 1.01,
+      "step": 522
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 5220,
+  "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": 1.3082708964409344e+16,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/checkpoint-522/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:112439a8bf818313a9112c0345790e09c2dd4279f702a6944e87378fe04ce172
+size 5432