Training in progress, step 63500, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
     "k_proj",
-    "gate_proj",
     "q_proj",
+    "up_proj",
+    "o_proj",
+    "gate_proj",
     "v_proj",
-    "down_proj",
-    "up_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 sha256:73903da31c9b9d848fa3dc081b0cc0b8784e6aef4a1ec1bce8df8211ea090227
+oid sha256:d2d9cff269682a6e1e23cdfca052e9f8c3fbccbf78453c2b7f70a6fe8d269149
 size 1882177840

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7f41f1d65446549e90258f21fed00d90b0c96c4f8a66571ccae685e2c8b63d5
+oid sha256:b2616a8e813904405bc939d148b53a7a439f7a299eb3700731870f85cd2fa724
 size 37161530

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c29d4681b39690eaaafbf2164900dcbb7e4adbbf215e4232929b945620d1964
+oid sha256:104890da2c59eb9ea543ff21a4559177df5b0fca409467c18f13be5167350e53
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bbd1aa5de53f2295365b6cba9c613b814db5492cf7e5c0c7f70f0bb0df8980c
+oid sha256:993c7bed5c196ded0eb58f1c8f7c3b64f5c12bdd352fa28eb7317e6257a44cb1
 size 1064

last-checkpoint/tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
-size 11421896
+oid sha256:83396048d512ec1f3178af0d7c1f79a226bba041822614b0e26a4fd2d4b55bf7
+size 11421995

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7005137100540396,
+  "epoch": 0.7060733426735162,
   "eval_steps": 1000,
-  "global_step": 63000,
+  "global_step": 63500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4940,6 +4940,41 @@
       "eval_samples_per_second": 2.041,
       "eval_steps_per_second": 2.041,
       "step": 63000
+    },
+    {
+      "epoch": 0.701625636577935,
+      "grad_norm": 0.0,
+      "learning_rate": 4.089320557540778e-05,
+      "loss": 1.9099,
+      "step": 63100
+    },
+    {
+      "epoch": 0.7027375631018302,
+      "grad_norm": 0.0,
+      "learning_rate": 4.061148317695832e-05,
+      "loss": 1.7735,
+      "step": 63200
+    },
+    {
+      "epoch": 0.7038494896257256,
+      "grad_norm": 0.0,
+      "learning_rate": 4.033048708563717e-05,
+      "loss": 1.8294,
+      "step": 63300
+    },
+    {
+      "epoch": 0.7049614161496208,
+      "grad_norm": 0.0,
+      "learning_rate": 4.005022073795828e-05,
+      "loss": 1.8543,
+      "step": 63400
+    },
+    {
+      "epoch": 0.7060733426735162,
+      "grad_norm": 0.0,
+      "learning_rate": 3.97706875615109e-05,
+      "loss": 1.9948,
+      "step": 63500
     }
   ],
   "logging_steps": 100,
@@ -4959,7 +4994,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.181810744019456e+17,
+  "total_flos": 1.186485573238272e+17,
   "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:ec38d3cfba225c81db568142403f6ae933af30fd8d4c51ca61ad487333f0fdad
+oid sha256:d738de42803f5441d68d35f8b7efcdaf6fb3c40d177d3ebb15d523d13779cf1f
 size 5496