Training in progress, epoch 0, checkpoint

checkpoint-187/adapter_config.json

@@ -1,6 +1,6 @@
 {
   "auto_mapping": null,
-  "base_model_name_or_path": "Qwen/Qwen1.5-4B",
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,

checkpoint-187/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96d9a28517e4b46642e385c718815d1c2e3c822b25b493187df08d9caae0590f
+size 143269386

checkpoint-187/added_tokens.json

@@ -1,5 +1,5 @@
 {
-  "<|endoftext|>": 151643,
-  "<|im_end|>": 151645,
-  "<|im_start|>": 151644
+  "</s>": 2,
+  "<s>": 1,
+  "<unk>": 0
 }

checkpoint-187/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd4c1f068fe69b249d42ac58a4037edcc9ac965d89b360b2802f0eea5dfad386
-size 224537202
+oid sha256:9c65108e2d9e926d2da3cbc971a4bf159bc925af354e922d453fe3b7e32ed465
+size 286585234

checkpoint-187/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8678a168ec4bc14647381e4ba4b9342409173ece538fd3a024d11bd3788ea53
+oid sha256:e6b111924d6e3cbbdfd36066ff90646c3759b4dcf1a00bcf21dd99512c23097f
 size 15024

checkpoint-187/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d69373d70bec4b6b8f40dc2551d226d027081f161e610f6b91ab26d18c6a68ac
+oid sha256:a5fef137284383c947d99523bddf3ea5c49e4fde63783d64916a2ad51c8a6683
 size 15024

checkpoint-187/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f94b2d30626f03816b9521115d5e1764867fd9c043ac4cac518cab21cd04f5bd
+oid sha256:a9c2339452f053bb04a6609c41d6d1d72741b59f234b1dfef9a7e3c0c7fb1813
 size 15024

checkpoint-187/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ef6e80422799fbfe22eaaa11bce5f2d92de8c4566904c08eca86fc4dd8c699c
+oid sha256:d51636ed1d34f62df811ec79010580465dc51af2d5ddbf75db0115d78c3689b3
 size 15024

checkpoint-187/special_tokens_map.json

@@ -1,14 +1,6 @@
 {
-  "additional_special_tokens": [
-    "<|im_start|>",
-    "<|im_end|>"
-  ],
-  "eos_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": "<|endoftext|>"
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "</s>",
+  "unk_token": "<unk>"
 }

checkpoint-187/tokenizer.model

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

checkpoint-187/tokenizer_config.json

@@ -1,24 +1,23 @@
 {
-  "add_prefix_space": false,
   "added_tokens_decoder": {
-    "151643": {
-      "content": "<|endoftext|>",
+    "0": {
+      "content": "<unk>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "151644": {
-      "content": "<|im_start|>",
+    "1": {
+      "content": "<s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "151645": {
-      "content": "<|im_end|>",
+    "2": {
+      "content": "</s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -26,18 +25,16 @@
       "special": true
     }
   },
-  "additional_special_tokens": [
-    "<|im_start|>",
-    "<|im_end|>"
-  ],
-  "bos_token": null,
-  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "<|endoftext|>",
-  "errors": "replace",
-  "model_max_length": 32768,
-  "pad_token": "<|endoftext|>",
-  "split_special_tokens": false,
-  "tokenizer_class": "Qwen2Tokenizer",
-  "unk_token": null
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
 }

checkpoint-187/trainer_state.json

@@ -9,51 +9,36 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.5333333333333333,
-      "grad_norm": 0.2081739604473114,
+      "epoch": 0.53,
       "learning_rate": 0.0005,
-      "loss": 1.7461,
+      "loss": 1.2462,
       "step": 100
     },
     {
-      "epoch": 0.9973333333333333,
-      "eval_accuracy": 0.6093004484304932,
-      "eval_loss": 1.6695144176483154,
-      "eval_runtime": 6.0389,
-      "eval_samples_per_second": 82.796,
-      "eval_steps_per_second": 10.432,
+      "epoch": 1.0,
+      "eval_accuracy": 0.6696470588235294,
+      "eval_loss": 1.1816030740737915,
+      "eval_runtime": 7.5359,
+      "eval_samples_per_second": 66.349,
+      "eval_steps_per_second": 8.36,
       "step": 187
     },
     {
-      "epoch": 0.9973333333333333,
-      "eval_exact_match": 15.8,
-      "eval_f1": 24.64418803418805,
-      "eval_qa_bleu": 12.64258947770803,
-      "eval_qa_exact_match": 0.116,
-      "eval_recite_bleu": 12.676034356605994,
+      "epoch": 1.0,
+      "eval_exact_match": 28.8,
+      "eval_f1": 38.19841269841268,
+      "eval_qa_bleu": 24.052327144564227,
+      "eval_qa_exact_match": 0.216,
+      "eval_recite_bleu": 16.828353493471358,
       "eval_recite_exact_match": 0.002,
       "step": 187
     }
   ],
   "logging_steps": 100,
   "max_steps": 9350,
-  "num_input_tokens_seen": 0,
   "num_train_epochs": 50,
   "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": 1.8886545306025984e+16,
-  "train_batch_size": 1,
+  "total_flos": 4.348367053887898e+16,
   "trial_name": null,
   "trial_params": null
 }

checkpoint-187/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b6061b8d6135a3f759c6b956a7afa194ea4a0f719fc2e4eb293c4d6c15c2590
-size 5304
+oid sha256:a28079dc7535e79a5e324b19b9af4575c5cbbdcf35a6916d09f5d38aff3423a1
+size 4728