Training in progress, step 40, checkpoint

last-checkpoint/config.json

@@ -1,28 +1,31 @@
 {
-  "_name_or_path": "unsloth/OpenHermes-2.5-Mistral-7B",
+  "_name_or_path": "facebook/opt-125m",
+  "_remove_final_layer_norm": false,
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
   "architectures": [
-    "MistralForCausalLM"
+    "OPTForCausalLM"
   ],
   "attention_dropout": 0.0,
-  "bos_token_id": 1,
-  "eos_token_id": 32000,
-  "head_dim": 128,
-  "hidden_act": "silu",
-  "hidden_size": 4096,
-  "initializer_range": 0.02,
-  "intermediate_size": 14336,
-  "max_position_embeddings": 32768,
-  "model_type": "mistral",
-  "num_attention_heads": 32,
-  "num_hidden_layers": 32,
-  "num_key_value_heads": 8,
-  "pad_token_id": 0,
-  "rms_norm_eps": 1e-05,
-  "rope_theta": 10000.0,
-  "sliding_window": 4096,
-  "tie_word_embeddings": false,
+  "bos_token_id": 2,
+  "do_layer_norm_before": true,
+  "dropout": 0.1,
+  "enable_bias": true,
+  "eos_token_id": 2,
+  "ffn_dim": 3072,
+  "hidden_size": 768,
+  "init_std": 0.02,
+  "layer_norm_elementwise_affine": true,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 2048,
+  "model_type": "opt",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "prefix": "</s>",
   "torch_dtype": "bfloat16",
   "transformers_version": "4.48.1",
   "use_cache": false,
-  "vocab_size": 32002
+  "vocab_size": 50265,
+  "word_embed_proj_dim": 768
 }

last-checkpoint/generation_config.json

@@ -1,7 +1,8 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 1,
+  "bos_token_id": 2,
   "do_sample": true,
-  "eos_token_id": 32000,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
   "transformers_version": "4.48.1"
 }

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7632ba1b08e41a9688dc652015271c5554d97ca9c7a3699508fa42877e5f157f
-size 136062744
+oid sha256:020fb30959dcfbcac82451f41a438ae05e3b42759d7aef54dbd8b1b18fa92a0b
+size 250490408

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dcb4aaff4751c7031e867ff29e6e2b9b4b0674cc9dd1b3848e0ceb758301a28
-size 14710155092
+oid sha256:9872fc9d64a3810789ce509a7a6922036ba50d567eec659feeb8df060129157f
+size 255265850

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcc743e915af10eb8f02d681d8900320ed9cdeb606f6a873967440c8da7f4171
+oid sha256:4bd18683b863492ce631a94ee5584e11dd4d36cc792cbaecef9af926cbae3258
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af355680189f24fb86dbec91733b793b613ef2007cc1d98d0dda1baea0cfe447
+oid sha256:150e9d8ac7ca53b6542b3bcb586e54185b9e3192646438983c13148331580cfb
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cc519c300189fd8bf8532291017b4f18ca0e4ed4f300c5f1db28f7c2a306b1f
+oid sha256:734cf14d86163a569080064839ed18c1874440d23b1f6d1c9853d47632a8afe9
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43ab8fc2e16a3a3a411c16a904c939083a120546d1ba4e6b33896a8d98f82434
+oid sha256:807f31446b661fa88560ba5f27adce494a63b711698296f75f4ec55596cb0d16
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf50222ecfd70b80cfe785ca128782a0335e8f9b2dc7d9c6f9de53c31acf54fb
+oid sha256:5ddacfc5985aaaf9c5485d233a2647099f91b76cf2d14ec27180de14a96e3a08
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5459d8790300f0c26473f655cab63f95e275592efb1f11439d5dfe599c61078
+oid sha256:6362ec4db59fac739742d93389181b84a0b42aced1dd528d1bb6541d165d11b6
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4cc73916421b8a9ff178b961a13691f77d415880f0b12c4e0a3d44cdc1a5891
+oid sha256:ad8f7136ea7db91b7b021660c4455507a8ca0de1d5b8ee7e42f733779d6ecc04
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c72813dc00c3ca644b08ae1a69d75889c7a46e91ae3e1c0401df8a2aa23a9c8
+oid sha256:0b119d7dc6c4723bd70ab53c942895b56911d3f61b5a7093b269d2e567ab0602
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:572996e9dc190ff3f3a6efdf58de929f593fa2dd2f97d74fed7646828651b17f
+oid sha256:1bd85be8ff4bc728c66eadc82b696b848e3baf1ad51034e1c2a8d5d22b53d6ea
 size 1064

last-checkpoint/special_tokens_map.json

@@ -1,29 +1,29 @@
 {
   "bos_token": {
-    "content": "<s>",
+    "content": "</s>",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
-    "content": "<|im_end|>",
+    "content": "</s>",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   },
   "pad_token": {
-    "content": "<unk>",
+    "content": "<pad>",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   },
   "unk_token": {
-    "content": "<unk>",
+    "content": "</s>",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   }

last-checkpoint/tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04222cd76979c181cd3f72c3bf6982fe2a09d9f4b8f23d82902efde18f1d0668
-size 3506125
+oid sha256:4a80800503667fe0bd639ad10c33879f747ba1582f369b06abb21f3f65d5ad3b
+size 3558658

last-checkpoint/tokenizer_config.json

@@ -1,20 +1,11 @@
 {
   "add_bos_token": true,
-  "add_eos_token": false,
-  "add_prefix_space": true,
+  "add_prefix_space": false,
   "added_tokens_decoder": {
-    "0": {
-      "content": "<unk>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
     "1": {
-      "content": "<s>",
+      "content": "<pad>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -22,43 +13,21 @@
     "2": {
       "content": "</s>",
       "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "32000": {
-      "content": "<|im_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "32001": {
-      "content": "<|im_start|>",
-      "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
-  "additional_special_tokens": [],
-  "bos_token": "<s>",
-  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "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": "<|im_end|>",
+  "eos_token": "</s>",
+  "errors": "replace",
   "extra_special_tokens": {},
-  "legacy": true,
-  "model_max_length": 32768,
-  "pad_token": "<unk>",
-  "padding_side": "right",
-  "sp_model_kwargs": {},
-  "spaces_between_special_tokens": false,
-  "tokenizer_class": "LlamaTokenizer",
-  "trust_remote_code": false,
-  "unk_token": "<unk>",
-  "use_default_system_prompt": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "</s>",
   "use_fast": true
 }

last-checkpoint/trainer_state.json

@@ -1,7 +1,7 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7692307692307693,
+  "epoch": 8.0,
   "eval_steps": 200,
   "global_step": 40,
   "is_hyper_param_search": false,
@@ -9,46 +9,46 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.019230769230769232,
-      "eval_loss": 1.8673125505447388,
-      "eval_runtime": 14.7715,
-      "eval_samples_per_second": 101.615,
-      "eval_steps_per_second": 6.364,
+      "epoch": 0.2,
+      "eval_loss": 3.4542977809906006,
+      "eval_runtime": 1.9768,
+      "eval_samples_per_second": 759.323,
+      "eval_steps_per_second": 6.071,
       "step": 1
     },
     {
-      "epoch": 0.19230769230769232,
-      "grad_norm": 18.375,
-      "learning_rate": 6.666666666666667e-05,
-      "loss": 2.4377,
+      "epoch": 2.0,
+      "grad_norm": 2.578125,
+      "learning_rate": 0.00019980267284282717,
+      "loss": 6.0334,
       "step": 10
     },
     {
-      "epoch": 0.38461538461538464,
-      "grad_norm": 80.5,
-      "learning_rate": 0.00013333333333333334,
-      "loss": 2.8471,
+      "epoch": 4.0,
+      "grad_norm": 4.4375,
+      "learning_rate": 0.0001992114701314478,
+      "loss": 5.3149,
       "step": 20
     },
     {
-      "epoch": 0.5769230769230769,
-      "grad_norm": 1200.0,
-      "learning_rate": 0.0002,
-      "loss": 7.8725,
+      "epoch": 6.0,
+      "grad_norm": 6.65625,
+      "learning_rate": 0.0001982287250728689,
+      "loss": 4.8724,
       "step": 30
     },
     {
-      "epoch": 0.7692307692307693,
-      "grad_norm": 37.25,
-      "learning_rate": 0.00019984815164333163,
-      "loss": 13.1972,
+      "epoch": 8.0,
+      "grad_norm": 3.5,
+      "learning_rate": 0.0001968583161128631,
+      "loss": 4.5259,
       "step": 40
     }
   ],
   "logging_steps": 10,
-  "max_steps": 600,
+  "max_steps": 500,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 12,
+  "num_train_epochs": 100,
   "save_steps": 40,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -62,8 +62,8 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.592056868320051e+16,
-  "train_batch_size": 2,
+  "total_flos": 5351260815360000.0,
+  "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null
 }

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53ebcd35271d188c087a5f00ee35959f144cc8fbcdfc0d1744678c3f065510bd
-size 6776
+oid sha256:f3d5f1e240ecc8a87b6c5953fd6de84410c7aff5f9646db311ea17ff72210b93
+size 6840