Upload folder using huggingface_hub

checkpoints/checkpoint-196/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-196/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-196/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bab26d660ef41409ed6091e5528693ab660830219ddc031ad534e05daccd1ac
+size 388979624

checkpoints/checkpoint-196/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e42c49afe99aa1fb66194edd4accdf4f737b5c59be9cab49e7568bf4761e6b12
+size 778027770

checkpoints/checkpoint-196/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ab4163c79d02a2b1cd5e87832e03656d66b051535f06b7e0f0faade52cd7bd7
+size 14244

checkpoints/checkpoint-196/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b29ce54c5709d7d62d31c4956f2a45f405faece035303224ba31dff63c33cc7b
+size 1064

checkpoints/checkpoint-196/trainer_state.json

@@ -0,0 +1,94 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 196,
+  "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
+    }
+  ],
+  "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": 3.191382263395123e+16,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/checkpoint-196/training_args.bin

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