Training in progress, step 50, checkpoint

last-checkpoint/adapter_config.json

@@ -23,10 +23,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "o_proj",
+    "q_proj",
     "k_proj",
-    "q_proj"
+    "v_proj",
+    "o_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 sha256:14851adaa9e05434ee1f37e933208a49edac7f16ff4ae446ef063be05cef3f23
+oid sha256:788f721f77b1d913a8b39bfad7d410c920b93d9228bd39aa0818a75a6d1ba7e5
 size 5991064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33c3cc3ee5bb0b305a4fee738020f7834021669ef0f94f68acde11f366850bec
+oid sha256:62bf1f6c6259d7ba8524d5501488f59e70f0242d124e45bbdcc8a547ff5660f3
 size 3875002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76b9fde5dce7e940b3874aa3cffeaaf4c858dbb7bcd23b53c0ae370065b6c604
+oid sha256:bdc875138895871a875d3239f8cb1e091d137772294fc52a0696aafd459bed5c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d31dc31a119769737d72f3df4c8cdf99522596cafc12bf2eea05a4ff374f599c
+oid sha256:9b80fcc7599efca0c6313d990c467c2eb3001742b23ddaadc22e3499c12cea79
 size 1064

last-checkpoint/trainer_state.json

@@ -2,117 +2,47 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.009890218573830482,
+  "epoch": 0.0032967395246101604,
   "eval_steps": 500,
-  "global_step": 150,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.0006593479049220321,
-      "grad_norm": 5.685938835144043,
+      "grad_norm": 4.714463233947754,
       "learning_rate": 0.0002,
-      "loss": 4.2492,
+      "loss": 4.214,
       "step": 10
     },
     {
       "epoch": 0.0013186958098440641,
-      "grad_norm": 7.900416374206543,
+      "grad_norm": 7.59287691116333,
       "learning_rate": 0.0002,
-      "loss": 2.1794,
+      "loss": 2.1247,
       "step": 20
     },
     {
       "epoch": 0.001978043714766096,
-      "grad_norm": 2.213648557662964,
+      "grad_norm": 1.9915987253189087,
       "learning_rate": 0.0002,
-      "loss": 1.7103,
+      "loss": 1.6737,
       "step": 30
     },
     {
       "epoch": 0.0026373916196881283,
-      "grad_norm": 2.4948573112487793,
+      "grad_norm": 1.6922399997711182,
       "learning_rate": 0.0002,
-      "loss": 1.5154,
+      "loss": 1.495,
       "step": 40
     },
     {
       "epoch": 0.0032967395246101604,
-      "grad_norm": 2.5954508781433105,
+      "grad_norm": 2.0545172691345215,
       "learning_rate": 0.0002,
-      "loss": 1.2728,
+      "loss": 1.2314,
       "step": 50
-    },
-    {
-      "epoch": 0.003956087429532192,
-      "grad_norm": 1.7071881294250488,
-      "learning_rate": 0.0002,
-      "loss": 1.6193,
-      "step": 60
-    },
-    {
-      "epoch": 0.004615435334454225,
-      "grad_norm": 2.5582172870635986,
-      "learning_rate": 0.0002,
-      "loss": 1.3123,
-      "step": 70
-    },
-    {
-      "epoch": 0.0052747832393762566,
-      "grad_norm": 1.731862187385559,
-      "learning_rate": 0.0002,
-      "loss": 1.2874,
-      "step": 80
-    },
-    {
-      "epoch": 0.005934131144298289,
-      "grad_norm": 1.6525731086730957,
-      "learning_rate": 0.0002,
-      "loss": 1.222,
-      "step": 90
-    },
-    {
-      "epoch": 0.006593479049220321,
-      "grad_norm": 1.7500087022781372,
-      "learning_rate": 0.0002,
-      "loss": 1.0816,
-      "step": 100
-    },
-    {
-      "epoch": 0.007252826954142353,
-      "grad_norm": 2.4738411903381348,
-      "learning_rate": 0.0002,
-      "loss": 1.4273,
-      "step": 110
-    },
-    {
-      "epoch": 0.007912174859064385,
-      "grad_norm": 1.6450600624084473,
-      "learning_rate": 0.0002,
-      "loss": 1.272,
-      "step": 120
-    },
-    {
-      "epoch": 0.008571522763986417,
-      "grad_norm": 1.6056126356124878,
-      "learning_rate": 0.0002,
-      "loss": 1.2377,
-      "step": 130
-    },
-    {
-      "epoch": 0.00923087066890845,
-      "grad_norm": 1.706062912940979,
-      "learning_rate": 0.0002,
-      "loss": 1.2175,
-      "step": 140
-    },
-    {
-      "epoch": 0.009890218573830482,
-      "grad_norm": 2.413339614868164,
-      "learning_rate": 0.0002,
-      "loss": 1.1407,
-      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -132,7 +62,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 259097708531712.0,
+  "total_flos": 86209240154112.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c7511702f18d8ac213dc65da12f19fd71052f783eb5d7f8d09cb8b9aec226f3
+oid sha256:1f35053563362c1def6be0aee6e36b447f4c27182c14ba0c6bf80a20f0a3c3cf
 size 5368