Upload folder using huggingface_hub

adapter_config.json

@@ -19,10 +19,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "query_key_value",
     "dense",
-    "dense_4h_to_h",
-    "dense_h_to_4h"
+    "query_key_value",
+    "dense_h_to_4h",
+    "dense_4h_to_h"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c6fbc8839039d81518e809e09d04f26d0b62532c6bba65cc594b3d72b56418f
+oid sha256:7bebd68776a4a61cb1f4f81939eaf7f8e14cde232d04f0af2894676460b6433c
 size 134235712

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fcb6340b982aa0e8d5ec80efe728b52fbfcffab7aceaed128ea70997a523b77
+oid sha256:a928ccde6a9c2011fa546fdb58512b2cab3585ac2aac2aac229b06dfffabdec4
 size 268514874

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ea94740a278d2cdc43335e117d4b3125aa15fdbf70cc95cca4937d85340fc2b
+oid sha256:a2409359a63e121485fe24a344ba36e669f278d392404a09304404248de3e122
 size 14244

special_tokens_map.json

@@ -1,20 +1,4 @@
 {
-  "additional_special_tokens": [
-    {
-      "content": "<|im_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "<|im_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    }
-  ],
   "bos_token": {
     "content": "<|endoftext|>",
     "lstrip": false,

tokenizer.json

@@ -235,24 +235,6 @@
     },
     {
       "id": 50277,
-      "content": "<|im_end|>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
-    },
-    {
-      "id": 50278,
-      "content": "<|im_start|>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
-    },
-    {
-      "id": 50279,
       "content": "[PAD]",
       "single_word": false,
       "lstrip": false,

tokenizer_config.json

@@ -202,22 +202,6 @@
       "special": false
     },
     "50277": {
-      "content": "<|im_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "50278": {
-      "content": "<|im_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "50279": {
       "content": "[PAD]",
       "lstrip": false,
       "normalized": false,
@@ -226,10 +210,6 @@
       "special": true
     }
   },
-  "additional_special_tokens": [
-    "<|im_end|>",
-    "<|im_start|>"
-  ],
   "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",

trainer_state.json

@@ -11,145 +11,145 @@
     {
       "epoch": 0.04,
       "learning_rate": 0.0002,
-      "loss": 2.2783,
+      "loss": 2.3695,
       "step": 2
     },
     {
       "epoch": 0.08,
       "learning_rate": 0.0002,
-      "loss": 2.5108,
+      "loss": 2.3951,
       "step": 4
     },
     {
       "epoch": 0.12,
       "learning_rate": 0.0002,
-      "loss": 2.6053,
+      "loss": 2.5973,
       "step": 6
     },
     {
       "epoch": 0.16,
       "learning_rate": 0.0002,
-      "loss": 2.8587,
+      "loss": 2.5197,
       "step": 8
     },
     {
       "epoch": 0.21,
       "learning_rate": 0.0002,
-      "loss": 2.8002,
+      "loss": 2.5993,
       "step": 10
     },
     {
       "epoch": 0.25,
       "learning_rate": 0.0002,
-      "loss": 3.4071,
+      "loss": 2.7419,
       "step": 12
     },
     {
       "epoch": 0.29,
       "learning_rate": 0.0002,
-      "loss": 2.2816,
+      "loss": 2.2986,
       "step": 14
     },
     {
       "epoch": 0.33,
       "learning_rate": 0.0002,
-      "loss": 2.6214,
+      "loss": 2.3248,
       "step": 16
     },
     {
       "epoch": 0.37,
       "learning_rate": 0.0002,
-      "loss": 2.4466,
+      "loss": 2.5489,
       "step": 18
     },
     {
       "epoch": 0.41,
       "learning_rate": 0.0002,
-      "loss": 2.7186,
+      "loss": 2.407,
       "step": 20
     },
     {
       "epoch": 0.45,
       "learning_rate": 0.0002,
-      "loss": 2.6705,
+      "loss": 2.59,
       "step": 22
     },
     {
       "epoch": 0.49,
       "learning_rate": 0.0002,
-      "loss": 3.3761,
+      "loss": 2.6604,
       "step": 24
     },
     {
       "epoch": 0.53,
       "learning_rate": 0.0002,
-      "loss": 2.2793,
+      "loss": 2.134,
       "step": 26
     },
     {
       "epoch": 0.57,
       "learning_rate": 0.0002,
-      "loss": 2.2849,
+      "loss": 2.2908,
       "step": 28
     },
     {
       "epoch": 0.62,
       "learning_rate": 0.0002,
-      "loss": 2.3829,
+      "loss": 2.4975,
       "step": 30
     },
     {
       "epoch": 0.66,
       "learning_rate": 0.0002,
-      "loss": 2.6203,
+      "loss": 2.4533,
       "step": 32
     },
     {
       "epoch": 0.7,
       "learning_rate": 0.0002,
-      "loss": 2.5967,
+      "loss": 2.4644,
       "step": 34
     },
     {
       "epoch": 0.74,
       "learning_rate": 0.0002,
-      "loss": 2.7552,
+      "loss": 2.6187,
       "step": 36
     },
     {
       "epoch": 0.78,
       "learning_rate": 0.0002,
-      "loss": 2.1381,
+      "loss": 2.137,
       "step": 38
     },
     {
       "epoch": 0.82,
       "learning_rate": 0.0002,
-      "loss": 2.2939,
+      "loss": 2.368,
       "step": 40
     },
     {
       "epoch": 0.86,
       "learning_rate": 0.0002,
-      "loss": 2.5408,
+      "loss": 2.4951,
       "step": 42
     },
     {
       "epoch": 0.9,
       "learning_rate": 0.0002,
-      "loss": 2.4259,
+      "loss": 2.4786,
       "step": 44
     },
     {
       "epoch": 0.94,
       "learning_rate": 0.0002,
-      "loss": 2.5202,
+      "loss": 2.5544,
       "step": 46
     },
     {
       "epoch": 0.98,
       "learning_rate": 0.0002,
-      "loss": 2.5082,
+      "loss": 2.6641,
       "step": 48
     }
   ],
@@ -158,7 +158,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 500,
-  "total_flos": 2050368575963136.0,
+  "total_flos": 2050091535802368.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbb5d771a6d1a018774cf9649db97eccab93bd3525027d97d1a3b3ef065d42e8
+oid sha256:c192e600688dd01de21da2985b51206f8f07a168a8b5675a50f80ace12a3a17f
 size 4728