Training in progress, epoch 0, checkpoint

last-checkpoint/README.md

@@ -1,5 +1,5 @@
 ---
-base_model: oopsung/llama2-7b-n-ox-test-v1
+base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
 library_name: peft
 ---
 

last-checkpoint/adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "oopsung/llama2-7b-n-ox-test-v1",
+  "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
   "bias": "none",
   "fan_in_fan_out": null,
   "inference_mode": true,
@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "v_proj",
-    "up_proj",
     "q_proj",
-    "down_proj",
+    "v_proj",
+    "o_proj",
     "gate_proj",
-    "k_proj"
+    "up_proj",
+    "k_proj",
+    "down_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 sha256:7e72b4a3235c259913087ac0799deb5f0a9ce95fa5a2731f32072330633125a2
-size 80013120
+oid sha256:91a9ea1223ba85bbea9348c544be11652f89e0e757979feed1bcb01f6c918891
+size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:102d34f3f27b40ee77ec12e016d974012f097b4b96ba45b8d940f87321cddd34
-size 41119636
+oid sha256:336c1293365b64ddb78543f3bc45d81537f442d08bc1806978f0ed670257d124
+size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7bbb9e6b1248c3560ef0c4d2a18853bb3b1d23161e5fbf5d045daee6827a56f
+oid sha256:a833f22f25ea3834727974efdfc06b3927711900cd9acb75c7c0258b248c9673
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:f883fd9393081a5c2e54691be1749bef50e284275a9e7a1c589cf11727a2e22b
 size 1064

last-checkpoint/tokenizer.model

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

last-checkpoint/tokenizer_config.json

@@ -26,46 +26,6 @@
       "rstrip": false,
       "single_word": false,
       "special": true
-    },
-    "46331": {
-      "content": "<|sep|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "46332": {
-      "content": "<|endoftext|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "46333": {
-      "content": "<|acc|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "46334": {
-      "content": "<|rrn|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "46335": {
-      "content": "<|tel|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
     }
   },
   "bos_token": "<s>",
@@ -73,8 +33,9 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "legacy": false,
-  "model_max_length": 1000000000000000019884624838656,
+  "model_max_length": 2048,
   "pad_token": "</s>",
+  "padding_side": "right",
   "sp_model_kwargs": {},
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": "<unk>",

last-checkpoint/trainer_state.json

@@ -1,121 +1,41 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.005608524957936063,
-  "eval_steps": 3,
-  "global_step": 10,
+  "epoch": 0.00013455328310010763,
+  "eval_steps": 500,
+  "global_step": 2,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.0005608524957936063,
-      "grad_norm": NaN,
-      "learning_rate": 2e-05,
-      "loss": 0.0,
-      "step": 1
-    },
-    {
-      "epoch": 0.0005608524957936063,
-      "eval_loss": NaN,
-      "eval_runtime": 23.6156,
-      "eval_samples_per_second": 31.801,
-      "eval_steps_per_second": 15.922,
+      "epoch": 6.727664155005382e-05,
+      "grad_norm": 17.90272331237793,
+      "learning_rate": 0.0001,
+      "loss": 7.986,
       "step": 1
     },
     {
-      "epoch": 0.0011217049915872126,
-      "grad_norm": NaN,
-      "learning_rate": 4e-05,
-      "loss": 0.0,
+      "epoch": 0.00013455328310010763,
+      "grad_norm": 3.7075886726379395,
+      "learning_rate": 0.0002,
+      "loss": 2.0306,
       "step": 2
     },
     {
-      "epoch": 0.0016825574873808188,
-      "grad_norm": NaN,
-      "learning_rate": 6e-05,
-      "loss": 0.0,
-      "step": 3
-    },
-    {
-      "epoch": 0.0016825574873808188,
-      "eval_loss": NaN,
-      "eval_runtime": 22.074,
-      "eval_samples_per_second": 34.022,
-      "eval_steps_per_second": 17.034,
-      "step": 3
-    },
-    {
-      "epoch": 0.002243409983174425,
-      "grad_norm": NaN,
-      "learning_rate": 8e-05,
-      "loss": 0.0,
-      "step": 4
-    },
-    {
-      "epoch": 0.0028042624789680315,
-      "grad_norm": NaN,
-      "learning_rate": 0.0001,
-      "loss": 0.0,
-      "step": 5
-    },
-    {
-      "epoch": 0.0033651149747616375,
-      "grad_norm": NaN,
-      "learning_rate": 0.00012,
-      "loss": 0.0,
-      "step": 6
-    },
-    {
-      "epoch": 0.0033651149747616375,
-      "eval_loss": NaN,
-      "eval_runtime": 22.2246,
-      "eval_samples_per_second": 33.791,
-      "eval_steps_per_second": 16.918,
-      "step": 6
-    },
-    {
-      "epoch": 0.003925967470555244,
-      "grad_norm": NaN,
-      "learning_rate": 0.00014,
-      "loss": 0.0,
-      "step": 7
-    },
-    {
-      "epoch": 0.00448681996634885,
-      "grad_norm": NaN,
-      "learning_rate": 0.00016,
-      "loss": 0.0,
-      "step": 8
-    },
-    {
-      "epoch": 0.005047672462142457,
-      "grad_norm": NaN,
-      "learning_rate": 0.00018,
-      "loss": 0.0,
-      "step": 9
-    },
-    {
-      "epoch": 0.005047672462142457,
-      "eval_loss": NaN,
-      "eval_runtime": 22.2714,
-      "eval_samples_per_second": 33.72,
-      "eval_steps_per_second": 16.883,
-      "step": 9
-    },
-    {
-      "epoch": 0.005608524957936063,
-      "grad_norm": NaN,
-      "learning_rate": 0.0002,
-      "loss": 0.0,
-      "step": 10
+      "epoch": 0.00013455328310010763,
+      "eval_loss": 2.1211705207824707,
+      "eval_runtime": 5.4013,
+      "eval_samples_per_second": 27.956,
+      "eval_steps_per_second": 27.956,
+      "step": 2
     }
   ],
   "logging_steps": 1,
-  "max_steps": 10,
+  "max_steps": 2,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
-  "save_steps": 3,
+  "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -128,8 +48,8 @@
       "attributes": {}
     }
   },
-  "total_flos": 1725322437328896.0,
-  "train_batch_size": 2,
+  "total_flos": 1598699864064.0,
+  "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:c0a0205286a7bd4fca07ce15cfa80889162bf3c590f02085703f2bd7a8a716c0
+oid sha256:5f7cf9b3f4a9b6aee0af9bb352b3071b1f748975269b94023838baf634daee8c
 size 6776