Training in progress, step 40, checkpoint

last-checkpoint/config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "JackFram/llama-160m",
+  "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": 3072,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "num_key_value_heads": 12,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.1",
+  "use_cache": false,
+  "vocab_size": 32000
+}

last-checkpoint/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.48.1"
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:261167a02cc8283b0a081b707ccabbf6ad8738d83bfe1b149d0b86d11391cfc4
+size 324847240

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b685ef3228bdedef26059fa2aa0d7b947ed1a609d2113fd9069ec193fd9ed904
+size 330143034

last-checkpoint/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0df10be429c2412198f2c4c684866a8c921cbd0d9ee4c865077476da07bda410
+size 15984

last-checkpoint/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b14d8363b71c1e824421bf14a513f0f951f1c6c9b9494dcedc75b3fa1fecea91
+size 15984

last-checkpoint/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0d27a8e9aed69fdd3b729f8cbf6300af5e0e26e9226d0e2307b0cf80aff9030
+size 15984

last-checkpoint/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23de9e35ad029c7a59ff383920fe892474d8f295c2e2f82ec3e6f109f3f96960
+size 15984

last-checkpoint/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50724f43561b5c511c4e37bb1b8ec7e620ff22332c4f39576452e56a9e02d18d
+size 15984

last-checkpoint/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f8d108db37b78249e3b0beb22f6120e06fd369dd9fbaa19526994e040db5f9d
+size 15984

last-checkpoint/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e62597393912992a3de2b36aa1663274b75b96f6525f5504e64377c5049c51e
+size 15984

last-checkpoint/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b1f0a5c61bcbceb46a2a335e00a59c951081a94126a8ae4cc9a9102e012eb65
+size 15984

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea54818dbc15bd81d4941b71d5e2806c555d1a733f768c00c5f1a670e0a08fb1
+size 1064

last-checkpoint/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

last-checkpoint/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{ '### Instruction: ' + message['content'] + '\n\n' }}{% elif message['role'] == 'assistant' %}{{ '### Response: ' + message['content'] + eos_token}}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,85 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.047337278106508875,
+  "eval_steps": 20,
+  "global_step": 40,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.001183431952662722,
+      "eval_loss": 3.7497785091400146,
+      "eval_runtime": 2.512,
+      "eval_samples_per_second": 597.919,
+      "eval_steps_per_second": 37.42,
+      "step": 1
+    },
+    {
+      "epoch": 0.011834319526627219,
+      "grad_norm": Infinity,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 3.4365,
+      "step": 10
+    },
+    {
+      "epoch": 0.023668639053254437,
+      "grad_norm": Infinity,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 3.552,
+      "step": 20
+    },
+    {
+      "epoch": 0.023668639053254437,
+      "eval_loss": 3.752192735671997,
+      "eval_runtime": 2.5179,
+      "eval_samples_per_second": 596.534,
+      "eval_steps_per_second": 37.333,
+      "step": 20
+    },
+    {
+      "epoch": 0.03550295857988166,
+      "grad_norm": Infinity,
+      "learning_rate": 4.8e-05,
+      "loss": 3.6338,
+      "step": 30
+    },
+    {
+      "epoch": 0.047337278106508875,
+      "grad_norm": Infinity,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 3.7366,
+      "step": 40
+    },
+    {
+      "epoch": 0.047337278106508875,
+      "eval_loss": 3.750141143798828,
+      "eval_runtime": 2.4739,
+      "eval_samples_per_second": 607.148,
+      "eval_steps_per_second": 37.997,
+      "step": 40
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 40,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1087416530108416.0,
+  "train_batch_size": 2,
+  "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:e3927a780a19050660d6f43496927b2c83f4417df1111bdd9cabcdb728ccb7d8
+size 6712