Training in progress, epoch 0, checkpoint

last-checkpoint/README.md

@@ -1,5 +1,5 @@
 ---
-base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
+base_model: peft-internal-testing/tiny-dummy-qwen2
 library_name: peft
 ---
 

last-checkpoint/adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
+  "base_model_name_or_path": "peft-internal-testing/tiny-dummy-qwen2",
   "bias": "none",
   "fan_in_fan_out": null,
   "inference_mode": true,
@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj",
+    "gate_proj",
+    "up_proj",
     "down_proj",
     "o_proj",
-    "k_proj",
-    "up_proj",
-    "gate_proj"
+    "q_proj",
+    "v_proj",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b49608e88641713ee5a2f11cc0f9b4df4195c3ece8e936a8dd4dced5882d814
-size 25271744
+oid sha256:962989733c8e1dcc0e0690e5aba62ea9ee0a2fe2320c26da797d679be524ce34
+size 14696

last-checkpoint/added_tokens.json

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

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea761731c07c68e93df9c9f52a0c1f1bc01f318ce497dba7102ff183eda25794
-size 13685516
+oid sha256:b0d5995a7f8d2e9c18041e4897a7fb6d8d26f2b9cb8cc932d76f93e9c6ba5d02
+size 39398

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9999fe17ac6d10df0b24edf483ce019f56daddfb3edc069a21c03ccaa11df1b8
+oid sha256:99bcf5ac8488b2a4c6dbe42b144f3d1d61b237d080b40d4d50265b37a38585d5
 size 14244

last-checkpoint/special_tokens_map.json

@@ -1,27 +1,17 @@
 {
-  "bos_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
   "eos_token": {
-    "content": "</s>",
+    "content": "<|endoftext|>",
     "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>",
+    "content": "<|endoftext|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

last-checkpoint/tokenizer_config.json

@@ -1,26 +1,24 @@
 {
-  "add_bos_token": true,
-  "add_eos_token": false,
-  "add_prefix_space": null,
+  "add_prefix_space": false,
   "added_tokens_decoder": {
-    "0": {
-      "content": "<unk>",
+    "151643": {
+      "content": "<|endoftext|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "1": {
-      "content": "<s>",
+    "151644": {
+      "content": "<|im_start|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "2": {
-      "content": "</s>",
+    "151645": {
+      "content": "<|im_end|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -28,16 +26,18 @@
       "special": true
     }
   },
-  "bos_token": "<s>",
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
   "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "</s>",
-  "legacy": false,
-  "model_max_length": 2048,
-  "pad_token": "</s>",
-  "padding_side": "right",
-  "sp_model_kwargs": {},
-  "tokenizer_class": "LlamaTokenizer",
-  "unk_token": "<unk>",
-  "use_default_system_prompt": false
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
 }

last-checkpoint/trainer_state.json

@@ -10,24 +10,24 @@
   "log_history": [
     {
       "epoch": 6.727664155005382e-05,
-      "grad_norm": 16.59201431274414,
+      "grad_norm": 0.16293905675411224,
       "learning_rate": 0.0001,
-      "loss": 7.986,
+      "loss": 11.9692,
       "step": 1
     },
     {
       "epoch": 0.00013455328310010763,
-      "grad_norm": 3.2888948917388916,
+      "grad_norm": 0.024962667375802994,
       "learning_rate": 0.0002,
-      "loss": 2.0306,
+      "loss": 11.931,
       "step": 2
     },
     {
       "epoch": 0.00013455328310010763,
-      "eval_loss": 2.1215152740478516,
-      "eval_runtime": 5.4188,
-      "eval_samples_per_second": 27.866,
-      "eval_steps_per_second": 27.866,
+      "eval_loss": 11.93213939666748,
+      "eval_runtime": 0.7868,
+      "eval_samples_per_second": 191.922,
+      "eval_steps_per_second": 191.922,
       "step": 2
     }
   ],
@@ -48,7 +48,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1598699864064.0,
+  "total_flos": 7385088.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b6377427e4e4bf683c90c59945e864e887a68d19ec55ff4999690a80faf10af
+oid sha256:22638b0668381099b9bfb9ad1ae68a538422f5a5856f8437a6d2474cc7d04e26
 size 6776