Training in progress, step 40, checkpoint

last-checkpoint/README.md

@@ -1,5 +1,5 @@
 ---
-base_model: JackFram/llama-68m
+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": "JackFram/llama-68m",
+  "base_model_name_or_path": "peft-internal-testing/tiny-dummy-qwen2",
   "bias": "none",
   "eva_config": null,
   "exclude_modules": null,
@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "o_proj",
     "v_proj",
+    "o_proj",
+    "gate_proj",
     "q_proj",
-    "up_proj",
     "down_proj",
-    "k_proj"
+    "k_proj",
+    "up_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:bf6bc89ed515c11edca157585cc4d08f3b032c0ffd4314aa79333ca1f3c8d512
-size 18091656
+oid sha256:159277feec320a7592284f9e3696651e378c75cb98a9616d5fc9a41efc0eec40
+size 183784

last-checkpoint/added_tokens.json

@@ -1,4 +1,5 @@
 {
-  "<|im_end|>": 32000,
-  "<|im_start|>": 32001
+  "<|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:b12933aa23a0c560e75cf26a59069e1e7ada485e87376d133ef8818dfabd9bd9
-size 14710155092
+oid sha256:3c71a9e87aa3c595eecb7f30d889af53933360e76b6456ae393643c7d90dcacb
+size 236760

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f20d155a14d34cd1bb6d04e5de90f3224906e1758821edd752a8f1a9085a2db
+oid sha256:99ae411404197432466fcb959effa7956b7aabac6b0ee3018ce67d44282b87b1
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad18e870a176ca75a54f6620f83de92bdfd5a91302744d90bff8e5feae2fe0c5
+oid sha256:0e0c13bbed523a6d7bec142d7a3836e9629b2dc23935ee4a5086689a05f762e6
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9009a52be47b75834407dc5e146ed5360e6f23a35bff27bab34ef6fb47df1661
+oid sha256:29316b978407a35ab6f860f3a2bcf442e67f1f9bd92ef1016961e6d3aa0c3d14
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fb494a08fd57e7c6f63f06826c872164986e81b271996be0496671f713bdcc3
+oid sha256:45e9c496f59967ab95befd85ccf8b9fef5104a06d33cdbe2714ed501882c6167
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cd11d413bc67bf01de9a1a006e9e7655be307353028b25f5b3c299e5b6b7a44
+oid sha256:bcaaab9b4e9d97f524192da2cde7b8ea63f0956124955e5031658e7310a4fbcd
 size 1064

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": "<|im_end|>",
+    "content": "<|endoftext|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "pad_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
+    "content": "<|endoftext|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

last-checkpoint/tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04222cd76979c181cd3f72c3bf6982fe2a09d9f4b8f23d82902efde18f1d0668
-size 3506125
+oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
+size 11418266

last-checkpoint/tokenizer_config.json

@@ -1,64 +1,45 @@
 {
-  "add_bos_token": true,
-  "add_eos_token": false,
-  "add_prefix_space": true,
+  "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>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "2": {
-      "content": "</s>",
+    "151644": {
+      "content": "<|im_start|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "32000": {
+    "151645": {
       "content": "<|im_end|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
-    },
-    "32001": {
-      "content": "<|im_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
     }
   },
-  "additional_special_tokens": [],
-  "bos_token": "<s>",
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
   "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 %}",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
+  "eos_token": "<|endoftext|>",
+  "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,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
   "use_fast": true
 }

last-checkpoint/trainer_state.json

@@ -1,175 +1,71 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.9047619047619047,
-  "eval_steps": 200,
-  "global_step": 200,
+  "epoch": 1.3793103448275863,
+  "eval_steps": 16,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.009523809523809525,
-      "eval_loss": 1.873080849647522,
-      "eval_runtime": 27.7442,
-      "eval_samples_per_second": 54.101,
-      "eval_steps_per_second": 6.776,
+      "epoch": 0.034482758620689655,
+      "eval_loss": 11.93175220489502,
+      "eval_runtime": 0.8699,
+      "eval_samples_per_second": 173.589,
+      "eval_steps_per_second": 6.898,
       "step": 1
     },
     {
-      "epoch": 0.09523809523809523,
-      "grad_norm": 32.75,
-      "learning_rate": 6.666666666666667e-05,
-      "loss": 2.6922,
+      "epoch": 0.3448275862068966,
+      "grad_norm": 0.04096066579222679,
+      "learning_rate": 9.995728791936504e-05,
+      "loss": 11.9309,
       "step": 10
     },
     {
-      "epoch": 0.19047619047619047,
-      "grad_norm": 628.0,
-      "learning_rate": 0.00013333333333333334,
-      "loss": 3.47,
-      "step": 20
-    },
-    {
-      "epoch": 0.2857142857142857,
-      "grad_norm": 141.0,
-      "learning_rate": 0.0002,
-      "loss": 9.2162,
-      "step": 30
-    },
-    {
-      "epoch": 0.38095238095238093,
-      "grad_norm": 30.625,
-      "learning_rate": 0.00019984815164333163,
-      "loss": 8.4222,
-      "step": 40
-    },
-    {
-      "epoch": 0.47619047619047616,
-      "grad_norm": 44.75,
-      "learning_rate": 0.00019939306773179497,
-      "loss": 8.4529,
-      "step": 50
-    },
-    {
-      "epoch": 0.5714285714285714,
-      "grad_norm": 29.375,
-      "learning_rate": 0.00019863613034027224,
-      "loss": 8.0506,
-      "step": 60
-    },
-    {
-      "epoch": 0.6666666666666666,
-      "grad_norm": 25.375,
-      "learning_rate": 0.00019757963826274357,
-      "loss": 8.6481,
-      "step": 70
-    },
-    {
-      "epoch": 0.7619047619047619,
-      "grad_norm": 26.75,
-      "learning_rate": 0.00019622680003092503,
-      "loss": 7.9906,
-      "step": 80
-    },
-    {
-      "epoch": 0.8571428571428571,
-      "grad_norm": 33.25,
-      "learning_rate": 0.00019458172417006347,
-      "loss": 8.4843,
-      "step": 90
-    },
-    {
-      "epoch": 0.9523809523809523,
-      "grad_norm": 23.5,
-      "learning_rate": 0.00019264940672148018,
-      "loss": 7.4575,
-      "step": 100
-    },
-    {
-      "epoch": 1.0476190476190477,
-      "grad_norm": 16.25,
-      "learning_rate": 0.00019043571606975777,
-      "loss": 7.4497,
-      "step": 110
-    },
-    {
-      "epoch": 1.1428571428571428,
-      "grad_norm": 19.75,
-      "learning_rate": 0.0001879473751206489,
-      "loss": 7.3829,
-      "step": 120
-    },
-    {
-      "epoch": 1.2380952380952381,
-      "grad_norm": 13.6875,
-      "learning_rate": 0.00018519194088383273,
-      "loss": 7.3748,
-      "step": 130
-    },
-    {
-      "epoch": 1.3333333333333333,
-      "grad_norm": 25.0,
-      "learning_rate": 0.0001821777815225245,
-      "loss": 7.3801,
-      "step": 140
+      "epoch": 0.5517241379310345,
+      "eval_loss": 11.927915573120117,
+      "eval_runtime": 0.9134,
+      "eval_samples_per_second": 165.318,
+      "eval_steps_per_second": 6.569,
+      "step": 16
     },
     {
-      "epoch": 1.4285714285714286,
-      "grad_norm": 13.0625,
-      "learning_rate": 0.00017891405093963938,
-      "loss": 7.2868,
-      "step": 150
-    },
-    {
-      "epoch": 1.5238095238095237,
-      "grad_norm": 52.0,
-      "learning_rate": 0.00017541066097768963,
-      "loss": 7.2058,
-      "step": 160
-    },
-    {
-      "epoch": 1.619047619047619,
-      "grad_norm": 98.5,
-      "learning_rate": 0.00017167825131684513,
-      "loss": 7.2541,
-      "step": 170
-    },
-    {
-      "epoch": 1.7142857142857144,
-      "grad_norm": 10.8125,
-      "learning_rate": 0.00016772815716257412,
-      "loss": 7.1795,
-      "step": 180
+      "epoch": 0.6896551724137931,
+      "grad_norm": 0.10107108950614929,
+      "learning_rate": 9.847001329696653e-05,
+      "loss": 11.9282,
+      "step": 20
     },
     {
-      "epoch": 1.8095238095238095,
-      "grad_norm": 18.125,
-      "learning_rate": 0.00016357237482099684,
-      "loss": 7.0485,
-      "step": 190
+      "epoch": 1.0344827586206897,
+      "grad_norm": 0.04157465696334839,
+      "learning_rate": 9.491954909459895e-05,
+      "loss": 11.9236,
+      "step": 30
     },
     {
-      "epoch": 1.9047619047619047,
-      "grad_norm": 9.4375,
-      "learning_rate": 0.00015922352526649803,
-      "loss": 6.9094,
-      "step": 200
+      "epoch": 1.103448275862069,
+      "eval_loss": 11.921222686767578,
+      "eval_runtime": 0.939,
+      "eval_samples_per_second": 160.809,
+      "eval_steps_per_second": 6.39,
+      "step": 32
     },
     {
-      "epoch": 1.9047619047619047,
-      "eval_loss": 6.993889808654785,
-      "eval_runtime": 27.036,
-      "eval_samples_per_second": 55.519,
-      "eval_steps_per_second": 6.954,
-      "step": 200
+      "epoch": 1.3793103448275863,
+      "grad_norm": 0.025179261341691017,
+      "learning_rate": 8.945702546981969e-05,
+      "loss": 11.9214,
+      "step": 40
     }
   ],
   "logging_steps": 10,
-  "max_steps": 600,
+  "max_steps": 160,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 6,
-  "save_steps": 200,
+  "save_steps": 40,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -182,8 +78,8 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3980142170800128e+17,
-  "train_batch_size": 2,
+  "total_flos": 647500922880.0,
+  "train_batch_size": 7,
   "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:ef3eb8b3b2a8acd873a0906e2cee7771ee216bb2230a5edc2d984d58604ec971
-size 6776
+oid sha256:37476a182ec272b4a6a6254cda6d0ce55ff7d3844823bf9121f7eccf202f4723
+size 6648