Training in progress, step 500, checkpoint

last-checkpoint/config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 512,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 18,
+  "num_key_value_heads": 16,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.9.0",
+  "use_cache": false,
+  "vocab_size": 50257
+}

last-checkpoint/generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 0,
+  "transformers_version": "5.9.0",
+  "use_cache": true
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad6aeef38ed358f8048c115091424d7e45cd8e98e79fdc324106be4910f58c95
+size 4523108832

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2d76978d088fcb730ac283219f0e32e79d7d521d55adaf8f7006b69f804ac5c
+size 2911851147

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:098b29492211804ab324a36f37466821d948280bb74fce4ba895c03f13ecd878
+size 14645

last-checkpoint/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f77569c2e850b04af982cc8c1389f1430851448915c593b69e5da36ce05b71d7
+size 1383

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff3b68c80bb6e1918e0fcbbfb26fa72db3f12e89d05c20abd2bd696373cfaadc
+size 1465

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "is_local": false,
+  "local_files_only": false,
+  "max_length": 512,
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "stride": 0,
+  "tokenizer_class": "GPT2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<|endoftext|>"
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,112 @@
+{
+  "best_global_step": 500,
+  "best_metric": 1.041561245918274,
+  "best_model_checkpoint": "./sft-out/checkpoint-500",
+  "epoch": 0.8840267418089397,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08840267418089397,
+      "grad_norm": 2.867664337158203,
+      "learning_rate": 9.800000000000001e-06,
+      "loss": 1.6486582946777344,
+      "step": 50
+    },
+    {
+      "epoch": 0.17680534836178793,
+      "grad_norm": 2.999215841293335,
+      "learning_rate": 1.98e-05,
+      "loss": 1.3320436096191406,
+      "step": 100
+    },
+    {
+      "epoch": 0.26520802254268194,
+      "grad_norm": 2.5709331035614014,
+      "learning_rate": 1.998591477024944e-05,
+      "loss": 1.2357231903076171,
+      "step": 150
+    },
+    {
+      "epoch": 0.35361069672357587,
+      "grad_norm": 2.5824177265167236,
+      "learning_rate": 1.994254499970557e-05,
+      "loss": 1.2124821472167968,
+      "step": 200
+    },
+    {
+      "epoch": 0.44201337090446985,
+      "grad_norm": 2.1276214122772217,
+      "learning_rate": 1.987001203159941e-05,
+      "loss": 1.1784111785888671,
+      "step": 250
+    },
+    {
+      "epoch": 0.5304160450853639,
+      "grad_norm": 2.2801501750946045,
+      "learning_rate": 1.9768528617623674e-05,
+      "loss": 1.14390380859375,
+      "step": 300
+    },
+    {
+      "epoch": 0.6188187192662578,
+      "grad_norm": 2.245532989501953,
+      "learning_rate": 1.963839242611693e-05,
+      "loss": 1.1346678161621093,
+      "step": 350
+    },
+    {
+      "epoch": 0.7072213934471517,
+      "grad_norm": 2.0729880332946777,
+      "learning_rate": 1.947998516895103e-05,
+      "loss": 1.1167774963378907,
+      "step": 400
+    },
+    {
+      "epoch": 0.7956240676280457,
+      "grad_norm": 2.183257818222046,
+      "learning_rate": 1.9293771481904463e-05,
+      "loss": 1.0449161529541016,
+      "step": 450
+    },
+    {
+      "epoch": 0.8840267418089397,
+      "grad_norm": 2.2573604583740234,
+      "learning_rate": 1.9080297561805535e-05,
+      "loss": 1.0654985809326172,
+      "step": 500
+    },
+    {
+      "epoch": 0.8840267418089397,
+      "eval_loss": 1.041561245918274,
+      "eval_runtime": 27.497,
+      "eval_samples_per_second": 18.184,
+      "eval_steps_per_second": 2.291,
+      "step": 500
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 3000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "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": 1.9429307822186496e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52aac54416caad4b34920e41127850e89b5c804e419294fc519e1644c8414d0f
+size 5329