Training in progress, epoch 0

adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "gate_proj",
+    "k_proj",
+    "up_proj",
+    "down_proj",
+    "q_proj",
+    "o_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3aa69b2b3433f682d36a2a3b5037e414fd8e89220be652d187fbbb4d6210e8a6
+size 25271744

chat_template.jinja

@@ -0,0 +1,4 @@
+{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ 'System: ' + system_message + '</s>' + '
+' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '</s>' + '
+Assistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' + '
+' }}{% endif %}{% endfor %}

runs/Oct20_03-46-36_8b029ae94c29/events.out.tfevents.1760932037.8b029ae94c29.13540.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:258e38083ebcf5e46dfbf6027fc07421315eeff89c1722fc8656236e3693f574
+size 11064

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
+  }
+}

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "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>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_log.jsonl

@@ -0,0 +1,26 @@
+{"current_steps": 10, "total_steps": 250, "loss": 0.7296, "lr": 0.00019936113105200085, "epoch": 0.018885741265344664, "percentage": 4.0, "elapsed_time": "0:01:06", "remaining_time": "0:26:25"}
+{"current_steps": 20, "total_steps": 250, "loss": 0.1418, "lr": 0.0001971631732914674, "epoch": 0.03777148253068933, "percentage": 8.0, "elapsed_time": "0:02:09", "remaining_time": "0:24:47"}
+{"current_steps": 30, "total_steps": 250, "loss": 0.1158, "lr": 0.00019343289424566122, "epoch": 0.056657223796033995, "percentage": 12.0, "elapsed_time": "0:03:12", "remaining_time": "0:23:34"}
+{"current_steps": 40, "total_steps": 250, "loss": 0.1129, "lr": 0.00018822912264349534, "epoch": 0.07554296506137866, "percentage": 16.0, "elapsed_time": "0:04:16", "remaining_time": "0:22:25"}
+{"current_steps": 50, "total_steps": 250, "loss": 0.109, "lr": 0.00018163392507171842, "epoch": 0.09442870632672333, "percentage": 20.0, "elapsed_time": "0:05:18", "remaining_time": "0:21:15"}
+{"current_steps": 60, "total_steps": 250, "loss": 0.1082, "lr": 0.0001737513117358174, "epoch": 0.11331444759206799, "percentage": 24.0, "elapsed_time": "0:06:22", "remaining_time": "0:20:09"}
+{"current_steps": 70, "total_steps": 250, "loss": 0.1073, "lr": 0.00016470559615694446, "epoch": 0.13220018885741266, "percentage": 28.0, "elapsed_time": "0:07:25", "remaining_time": "0:19:04"}
+{"current_steps": 80, "total_steps": 250, "loss": 0.1036, "lr": 0.00015463943467342693, "epoch": 0.1510859301227573, "percentage": 32.0, "elapsed_time": "0:08:28", "remaining_time": "0:18:01"}
+{"current_steps": 90, "total_steps": 250, "loss": 0.0999, "lr": 0.0001437115766650933, "epoch": 0.16997167138810199, "percentage": 36.0, "elapsed_time": "0:09:32", "remaining_time": "0:16:57"}
+{"current_steps": 100, "total_steps": 250, "loss": 0.1009, "lr": 0.00013209436098072095, "epoch": 0.18885741265344666, "percentage": 40.0, "elapsed_time": "0:10:35", "remaining_time": "0:15:53"}
+{"current_steps": 110, "total_steps": 250, "loss": 0.0996, "lr": 0.00011997099805144069, "epoch": 0.2077431539187913, "percentage": 44.0, "elapsed_time": "0:11:39", "remaining_time": "0:14:50"}
+{"current_steps": 120, "total_steps": 250, "loss": 0.1015, "lr": 0.00010753268055279329, "epoch": 0.22662889518413598, "percentage": 48.0, "elapsed_time": "0:12:42", "remaining_time": "0:13:46"}
+{"current_steps": 130, "total_steps": 250, "loss": 0.1023, "lr": 9.497556818202306e-05, "epoch": 0.24551463644948066, "percentage": 52.0, "elapsed_time": "0:13:46", "remaining_time": "0:12:42"}
+{"current_steps": 140, "total_steps": 250, "loss": 0.1005, "lr": 8.249769410247239e-05, "epoch": 0.26440037771482533, "percentage": 56.0, "elapsed_time": "0:14:49", "remaining_time": "0:11:39"}
+{"current_steps": 150, "total_steps": 250, "loss": 0.0958, "lr": 7.029584184229653e-05, "epoch": 0.28328611898017, "percentage": 60.0, "elapsed_time": "0:15:52", "remaining_time": "0:10:35"}
+{"current_steps": 160, "total_steps": 250, "loss": 0.0972, "lr": 5.856244190067159e-05, "epoch": 0.3021718602455146, "percentage": 64.0, "elapsed_time": "0:16:57", "remaining_time": "0:09:32"}
+{"current_steps": 170, "total_steps": 250, "loss": 0.0977, "lr": 4.748253700387042e-05, "epoch": 0.3210576015108593, "percentage": 68.0, "elapsed_time": "0:18:00", "remaining_time": "0:08:28"}
+{"current_steps": 180, "total_steps": 250, "loss": 0.0975, "lr": 3.7230863870929964e-05, "epoch": 0.33994334277620397, "percentage": 72.0, "elapsed_time": "0:19:04", "remaining_time": "0:07:24"}
+{"current_steps": 190, "total_steps": 250, "loss": 0.0975, "lr": 2.7969097511209308e-05, "epoch": 0.3588290840415486, "percentage": 76.0, "elapsed_time": "0:20:06", "remaining_time": "0:06:21"}
+{"current_steps": 200, "total_steps": 250, "loss": 0.0968, "lr": 1.9843301512912327e-05, "epoch": 0.3777148253068933, "percentage": 80.0, "elapsed_time": "0:21:09", "remaining_time": "0:05:17"}
+{"current_steps": 210, "total_steps": 250, "loss": 0.0974, "lr": 1.2981624533047432e-05, "epoch": 0.39660056657223797, "percentage": 84.0, "elapsed_time": "0:22:13", "remaining_time": "0:04:13"}
+{"current_steps": 220, "total_steps": 250, "loss": 0.0979, "lr": 7.492279316554207e-06, "epoch": 0.4154863078375826, "percentage": 88.0, "elapsed_time": "0:23:15", "remaining_time": "0:03:10"}
+{"current_steps": 230, "total_steps": 250, "loss": 0.0998, "lr": 3.461836116672612e-06, "epoch": 0.4343720491029273, "percentage": 92.0, "elapsed_time": "0:24:18", "remaining_time": "0:02:06"}
+{"current_steps": 240, "total_steps": 250, "loss": 0.096, "lr": 9.538574303348813e-07, "epoch": 0.45325779036827196, "percentage": 96.0, "elapsed_time": "0:25:21", "remaining_time": "0:01:03"}
+{"current_steps": 250, "total_steps": 250, "loss": 0.0987, "lr": 7.895579618388827e-09, "epoch": 0.4721435316336166, "percentage": 100.0, "elapsed_time": "0:26:24", "remaining_time": "0:00:00"}
+{"current_steps": 250, "total_steps": 250, "epoch": 0.4721435316336166, "percentage": 100.0, "elapsed_time": "0:26:25", "remaining_time": "0:00:00"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dab7247fa84cbaaa8ec716eacb9ad44774956b37e7e8f4f5405f5c5a721d378
+size 6225