Training in progress, epoch 0

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "SeaLLMs/SeaLLMs-v3-7B-Chat",
+  "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",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "o_proj",
+    "v_proj",
+    "k_proj",
+    "q_proj",
+    "gate_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb5401531e732cf4694d8233b041dba1330b7b63affcd5c22924d64e6b68ccc7
+size 80792096

added_tokens.json

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

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
+size 11418266

tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% set system_message = 'You are a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_log.jsonl

@@ -0,0 +1,25 @@
+{"current_steps": 67, "total_steps": 1337, "loss": 2.005, "lr": 4.925373134328357e-07, "epoch": 0.05009345794392523, "percentage": 5.01, "elapsed_time": "0:01:29", "remaining_time": "0:28:14"}
+{"current_steps": 134, "total_steps": 1337, "loss": 1.9012, "lr": 9.925373134328357e-07, "epoch": 0.10018691588785046, "percentage": 10.02, "elapsed_time": "0:02:59", "remaining_time": "0:26:52"}
+{"current_steps": 201, "total_steps": 1337, "loss": 1.1013, "lr": 9.451371571072319e-07, "epoch": 0.1502803738317757, "percentage": 15.03, "elapsed_time": "0:04:28", "remaining_time": "0:25:17"}
+{"current_steps": 250, "total_steps": 1337, "eval_loss": 0.3121011257171631, "epoch": 0.18691588785046728, "percentage": 18.7, "elapsed_time": "0:06:00", "remaining_time": "0:26:06"}
+{"current_steps": 268, "total_steps": 1337, "loss": 0.391, "lr": 8.894430590191188e-07, "epoch": 0.20037383177570092, "percentage": 20.04, "elapsed_time": "0:06:23", "remaining_time": "0:25:30"}
+{"current_steps": 335, "total_steps": 1337, "loss": 0.2437, "lr": 8.337489609310058e-07, "epoch": 0.2504672897196262, "percentage": 25.06, "elapsed_time": "0:07:52", "remaining_time": "0:23:34"}
+{"current_steps": 402, "total_steps": 1337, "loss": 0.2037, "lr": 7.780548628428927e-07, "epoch": 0.3005607476635514, "percentage": 30.07, "elapsed_time": "0:09:22", "remaining_time": "0:21:47"}
+{"current_steps": 469, "total_steps": 1337, "loss": 0.1918, "lr": 7.223607647547797e-07, "epoch": 0.3506542056074766, "percentage": 35.08, "elapsed_time": "0:10:51", "remaining_time": "0:20:06"}
+{"current_steps": 500, "total_steps": 1337, "eval_loss": 0.18135082721710205, "epoch": 0.37383177570093457, "percentage": 37.4, "elapsed_time": "0:11:58", "remaining_time": "0:20:03"}
+{"current_steps": 536, "total_steps": 1337, "loss": 0.1797, "lr": 6.666666666666666e-07, "epoch": 0.40074766355140184, "percentage": 40.09, "elapsed_time": "0:12:45", "remaining_time": "0:19:04"}
+{"current_steps": 603, "total_steps": 1337, "loss": 0.1618, "lr": 6.109725685785536e-07, "epoch": 0.4508411214953271, "percentage": 45.1, "elapsed_time": "0:14:13", "remaining_time": "0:17:18"}
+{"current_steps": 670, "total_steps": 1337, "loss": 0.1627, "lr": 5.552784704904405e-07, "epoch": 0.5009345794392523, "percentage": 50.11, "elapsed_time": "0:15:41", "remaining_time": "0:15:37"}
+{"current_steps": 737, "total_steps": 1337, "loss": 0.1654, "lr": 4.995843724023275e-07, "epoch": 0.5510280373831775, "percentage": 55.12, "elapsed_time": "0:17:10", "remaining_time": "0:13:59"}
+{"current_steps": 750, "total_steps": 1337, "eval_loss": 0.15894462168216705, "epoch": 0.5607476635514018, "percentage": 56.1, "elapsed_time": "0:17:54", "remaining_time": "0:14:01"}
+{"current_steps": 804, "total_steps": 1337, "loss": 0.1507, "lr": 4.438902743142144e-07, "epoch": 0.6011214953271028, "percentage": 60.13, "elapsed_time": "0:19:05", "remaining_time": "0:12:39"}
+{"current_steps": 871, "total_steps": 1337, "loss": 0.1596, "lr": 3.881961762261014e-07, "epoch": 0.6512149532710281, "percentage": 65.15, "elapsed_time": "0:20:34", "remaining_time": "0:11:00"}
+{"current_steps": 938, "total_steps": 1337, "loss": 0.1499, "lr": 3.3250207813798835e-07, "epoch": 0.7013084112149532, "percentage": 70.16, "elapsed_time": "0:22:03", "remaining_time": "0:09:22"}
+{"current_steps": 1000, "total_steps": 1337, "eval_loss": 0.14763584733009338, "epoch": 0.7476635514018691, "percentage": 74.79, "elapsed_time": "0:23:52", "remaining_time": "0:08:02"}
+{"current_steps": 1005, "total_steps": 1337, "loss": 0.1237, "lr": 2.7680798004987534e-07, "epoch": 0.7514018691588785, "percentage": 75.17, "elapsed_time": "0:23:58", "remaining_time": "0:07:55"}
+{"current_steps": 1072, "total_steps": 1337, "loss": 0.1281, "lr": 2.2111388196176226e-07, "epoch": 0.8014953271028037, "percentage": 80.18, "elapsed_time": "0:25:25", "remaining_time": "0:06:17"}
+{"current_steps": 1139, "total_steps": 1337, "loss": 0.1394, "lr": 1.6541978387364923e-07, "epoch": 0.851588785046729, "percentage": 85.19, "elapsed_time": "0:26:53", "remaining_time": "0:04:40"}
+{"current_steps": 1206, "total_steps": 1337, "loss": 0.1227, "lr": 1.0972568578553615e-07, "epoch": 0.9016822429906542, "percentage": 90.2, "elapsed_time": "0:28:21", "remaining_time": "0:03:04"}
+{"current_steps": 1250, "total_steps": 1337, "eval_loss": 0.14381863176822662, "epoch": 0.9345794392523364, "percentage": 93.49, "elapsed_time": "0:29:45", "remaining_time": "0:02:04"}
+{"current_steps": 1273, "total_steps": 1337, "loss": 0.1298, "lr": 5.403158769742311e-08, "epoch": 0.9517757009345794, "percentage": 95.21, "elapsed_time": "0:30:16", "remaining_time": "0:01:31"}
+{"current_steps": 1337, "total_steps": 1337, "epoch": 0.9996261682242991, "percentage": 100.0, "elapsed_time": "0:31:44", "remaining_time": "0:00:00"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16fcac4492a2f361e87f9e79de2a724e709d239f646039491f366d20ef7e65c0
+size 5752