Upload folder using huggingface_hub

adapter_config.json

@@ -19,13 +19,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj",
-    "o_proj",
     "gate_proj",
-    "up_proj",
+    "down_proj",
     "k_proj",
-    "down_proj"
+    "up_proj",
+    "q_proj",
+    "o_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68ffb7728699344b9838f9afb7975fd02b29fe06bb1fbe0bc66591eed483fa3f
+oid sha256:6f299b6699081000cc932ccea777d615aff6b3ca5e926fd8ba5a4b70e7748a1f
 size 242266152

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e9a94707bb17ef5829b78f0d9c5987210c0c274f9b4c94292c5857bcb6a7ba5
+oid sha256:26e0c58ea98fb459c4bcd7cae48ed39f5b7bf4fc00c2021e394dc2ae8907e89c
 size 484650042

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:224bead7fd043b72a8e81bd036d7d5df846f092c760212f12210c387735e21a3
+oid sha256:bfc92f9528cf33c4015ed912bbf16f0a6174711d2175a8a77ab13193ae70847a
 size 14244

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81007ec48272bbdc4f9622c046f9c026bf8120ed11d1398fd97bb5168a6f3dda
+oid sha256:824a429c5f95423b97fd2ff7dc1e1dffcd96691286babb37392f00bfcecaeb1b
 size 1064

special_tokens_map.json

@@ -1,4 +1,20 @@
 {
+  "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
+    }
+  ],
   "eos_token": "<|endoftext|>",
   "pad_token": {
     "content": "<|endoftext|>",

tokenizer_config.json

@@ -1,5 +1,9 @@
 {
   "added_tokens_decoder": {},
+  "additional_special_tokens": [
+    "<|im_end|>",
+    "<|im_start|>"
+  ],
   "auto_map": {
     "AutoTokenizer": [
       "stabilityai/stablelm-2-1_6b--tokenization_arcade100k.Arcade100kTokenizer",

trainer_state.json

@@ -1,320 +1,218 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9944064636420137,
+  "epoch": 0.9990680335507922,
   "eval_steps": 500,
-  "global_step": 100,
+  "global_step": 67,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.02,
+      "epoch": 0.03,
       "learning_rate": 0.0002,
-      "loss": 2.3211,
+      "loss": 2.6207,
       "step": 2
     },
     {
-      "epoch": 0.04,
+      "epoch": 0.06,
       "learning_rate": 0.0002,
-      "loss": 2.1994,
+      "loss": 2.0637,
       "step": 4
     },
     {
-      "epoch": 0.06,
+      "epoch": 0.09,
       "learning_rate": 0.0002,
-      "loss": 2.1871,
+      "loss": 1.7145,
       "step": 6
     },
     {
-      "epoch": 0.08,
+      "epoch": 0.12,
       "learning_rate": 0.0002,
-      "loss": 2.1569,
+      "loss": 1.7226,
       "step": 8
     },
     {
-      "epoch": 0.1,
+      "epoch": 0.15,
       "learning_rate": 0.0002,
-      "loss": 2.1101,
+      "loss": 1.5185,
       "step": 10
     },
     {
-      "epoch": 0.12,
+      "epoch": 0.18,
       "learning_rate": 0.0002,
-      "loss": 2.1361,
+      "loss": 1.8167,
       "step": 12
     },
     {
-      "epoch": 0.14,
+      "epoch": 0.21,
       "learning_rate": 0.0002,
-      "loss": 2.002,
+      "loss": 2.1173,
       "step": 14
     },
     {
-      "epoch": 0.16,
+      "epoch": 0.24,
       "learning_rate": 0.0002,
-      "loss": 2.1144,
+      "loss": 2.4144,
       "step": 16
     },
     {
-      "epoch": 0.18,
+      "epoch": 0.27,
       "learning_rate": 0.0002,
-      "loss": 1.9981,
+      "loss": 2.7712,
       "step": 18
     },
     {
-      "epoch": 0.2,
+      "epoch": 0.3,
       "learning_rate": 0.0002,
-      "loss": 1.8518,
+      "loss": 1.5772,
       "step": 20
     },
     {
-      "epoch": 0.22,
+      "epoch": 0.33,
       "learning_rate": 0.0002,
-      "loss": 2.0797,
+      "loss": 1.5499,
       "step": 22
     },
     {
-      "epoch": 0.24,
+      "epoch": 0.36,
       "learning_rate": 0.0002,
-      "loss": 1.9593,
+      "loss": 1.5204,
       "step": 24
     },
     {
-      "epoch": 0.26,
+      "epoch": 0.39,
       "learning_rate": 0.0002,
-      "loss": 2.1172,
+      "loss": 1.3435,
       "step": 26
     },
     {
-      "epoch": 0.28,
+      "epoch": 0.42,
       "learning_rate": 0.0002,
-      "loss": 2.056,
+      "loss": 1.5878,
       "step": 28
     },
     {
-      "epoch": 0.3,
+      "epoch": 0.45,
       "learning_rate": 0.0002,
-      "loss": 1.9752,
+      "loss": 1.744,
       "step": 30
     },
     {
-      "epoch": 0.32,
+      "epoch": 0.48,
       "learning_rate": 0.0002,
-      "loss": 2.0642,
+      "loss": 2.0522,
       "step": 32
     },
     {
-      "epoch": 0.34,
+      "epoch": 0.51,
       "learning_rate": 0.0002,
-      "loss": 2.082,
+      "loss": 2.0968,
       "step": 34
     },
     {
-      "epoch": 0.36,
+      "epoch": 0.54,
       "learning_rate": 0.0002,
-      "loss": 2.0809,
+      "loss": 1.3657,
       "step": 36
     },
     {
-      "epoch": 0.38,
+      "epoch": 0.57,
       "learning_rate": 0.0002,
-      "loss": 1.9503,
+      "loss": 1.4401,
       "step": 38
     },
     {
-      "epoch": 0.4,
+      "epoch": 0.6,
       "learning_rate": 0.0002,
-      "loss": 1.9841,
+      "loss": 1.5278,
       "step": 40
     },
     {
-      "epoch": 0.42,
+      "epoch": 0.63,
       "learning_rate": 0.0002,
-      "loss": 1.954,
+      "loss": 1.0668,
       "step": 42
     },
     {
-      "epoch": 0.44,
+      "epoch": 0.66,
       "learning_rate": 0.0002,
-      "loss": 1.8861,
+      "loss": 1.361,
       "step": 44
     },
     {
-      "epoch": 0.46,
+      "epoch": 0.69,
       "learning_rate": 0.0002,
-      "loss": 1.9725,
+      "loss": 1.6086,
       "step": 46
     },
     {
-      "epoch": 0.48,
+      "epoch": 0.72,
       "learning_rate": 0.0002,
-      "loss": 1.8173,
+      "loss": 1.8953,
       "step": 48
     },
     {
-      "epoch": 0.5,
+      "epoch": 0.75,
       "learning_rate": 0.0002,
-      "loss": 1.9095,
+      "loss": 2.259,
       "step": 50
     },
     {
-      "epoch": 0.52,
+      "epoch": 0.78,
       "learning_rate": 0.0002,
-      "loss": 1.9165,
+      "loss": 1.7595,
       "step": 52
     },
     {
-      "epoch": 0.54,
+      "epoch": 0.81,
       "learning_rate": 0.0002,
-      "loss": 1.954,
+      "loss": 1.3564,
       "step": 54
     },
     {
-      "epoch": 0.56,
+      "epoch": 0.84,
       "learning_rate": 0.0002,
-      "loss": 2.0812,
+      "loss": 1.6172,
       "step": 56
     },
     {
-      "epoch": 0.58,
+      "epoch": 0.86,
       "learning_rate": 0.0002,
-      "loss": 1.9473,
+      "loss": 1.1223,
       "step": 58
     },
     {
-      "epoch": 0.6,
+      "epoch": 0.89,
       "learning_rate": 0.0002,
-      "loss": 2.0644,
+      "loss": 1.3858,
       "step": 60
     },
     {
-      "epoch": 0.62,
+      "epoch": 0.92,
       "learning_rate": 0.0002,
-      "loss": 2.0597,
+      "loss": 1.7015,
       "step": 62
     },
     {
-      "epoch": 0.64,
+      "epoch": 0.95,
       "learning_rate": 0.0002,
-      "loss": 1.9422,
+      "loss": 1.7062,
       "step": 64
     },
     {
-      "epoch": 0.66,
+      "epoch": 0.98,
       "learning_rate": 0.0002,
-      "loss": 1.8022,
+      "loss": 1.4214,
       "step": 66
-    },
-    {
-      "epoch": 0.68,
-      "learning_rate": 0.0002,
-      "loss": 1.9411,
-      "step": 68
-    },
-    {
-      "epoch": 0.7,
-      "learning_rate": 0.0002,
-      "loss": 1.8742,
-      "step": 70
-    },
-    {
-      "epoch": 0.72,
-      "learning_rate": 0.0002,
-      "loss": 1.8078,
-      "step": 72
-    },
-    {
-      "epoch": 0.74,
-      "learning_rate": 0.0002,
-      "loss": 1.9996,
-      "step": 74
-    },
-    {
-      "epoch": 0.76,
-      "learning_rate": 0.0002,
-      "loss": 1.7464,
-      "step": 76
-    },
-    {
-      "epoch": 0.78,
-      "learning_rate": 0.0002,
-      "loss": 1.8637,
-      "step": 78
-    },
-    {
-      "epoch": 0.8,
-      "learning_rate": 0.0002,
-      "loss": 1.9297,
-      "step": 80
-    },
-    {
-      "epoch": 0.82,
-      "learning_rate": 0.0002,
-      "loss": 1.9462,
-      "step": 82
-    },
-    {
-      "epoch": 0.84,
-      "learning_rate": 0.0002,
-      "loss": 1.9367,
-      "step": 84
-    },
-    {
-      "epoch": 0.86,
-      "learning_rate": 0.0002,
-      "loss": 1.9843,
-      "step": 86
-    },
-    {
-      "epoch": 0.88,
-      "learning_rate": 0.0002,
-      "loss": 2.0611,
-      "step": 88
-    },
-    {
-      "epoch": 0.89,
-      "learning_rate": 0.0002,
-      "loss": 1.8584,
-      "step": 90
-    },
-    {
-      "epoch": 0.91,
-      "learning_rate": 0.0002,
-      "loss": 1.8235,
-      "step": 92
-    },
-    {
-      "epoch": 0.93,
-      "learning_rate": 0.0002,
-      "loss": 1.9358,
-      "step": 94
-    },
-    {
-      "epoch": 0.95,
-      "learning_rate": 0.0002,
-      "loss": 1.854,
-      "step": 96
-    },
-    {
-      "epoch": 0.97,
-      "learning_rate": 0.0002,
-      "loss": 1.8953,
-      "step": 98
-    },
-    {
-      "epoch": 0.99,
-      "learning_rate": 0.0002,
-      "loss": 1.7185,
-      "step": 100
     }
   ],
   "logging_steps": 2,
-  "max_steps": 300,
+  "max_steps": 67,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 1,
   "save_steps": 500,
-  "total_flos": 1.3484808608858112e+16,
+  "total_flos": 4524039463452672.0,
   "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 sha256:11b52a2201929623074064b5575a45c1dca7a2d9070772a0ae7e2dd1e5c1225d
+oid sha256:0eca4a69f5ee77a28b437616dd0dfaf6f36ef44c125ff32adab8c8612689baa8
 size 4728