Upload fine-tuned checkpoint

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90ded5363c2db97ff3750527e380a2c1f5ec45ea549c35b83e8fc41c24e45755
+oid sha256:0539a36e6a74f2a3406db8fa6dca951caa7964905378b7db1054dcf33f2eb9db
 size 27297032

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b03510e887c64ac3a15f4caa9a6b07fa75481aedaca8cf441644a811a5addb9e
+oid sha256:46b2ca18f46519ce107b56d52f4fbfd44ce18c555787d3803f48d182d4ed3fe0
 size 54741195

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd779a83acd3715c3d89d4b2113b579f25c288a6885c23419474a59b3d94b13a
+oid sha256:56aaeecdd7e946f32ea405fcbda9013bb4265f7535e6c1c8a57deda409eecc43
 size 14645

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31c8db2337dd529c4305ba9ec942095fa6efc6b665b33070cf7956020c7f5bb6
+oid sha256:73418fb68e188969c98f7ed1c862c2617299d539423cbbbbdd8d7bf13c2ac383
 size 1465

trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 600,
-  "best_metric": 0.5126457214355469,
+  "best_global_step": 400,
+  "best_metric": 0.5587947964668274,
   "best_model_checkpoint": "./opencoder8b_finetuned/checkpoint-400",
-  "epoch": 3.0,
+  "epoch": 1.639344262295082,
   "eval_steps": 200,
-  "global_step": 732,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,35 +52,6 @@
       "eval_samples_per_second": 4.328,
       "eval_steps_per_second": 0.544,
       "step": 400
-    },
-    {
-      "epoch": 2.0491803278688523,
-      "grad_norm": 0.17177526652812958,
-      "learning_rate": 7.3625016623302155e-06,
-      "loss": 0.5556,
-      "step": 500
-    },
-    {
-      "epoch": 2.459016393442623,
-      "grad_norm": 0.26423564553260803,
-      "learning_rate": 6.022760330631006e-06,
-      "loss": 0.5291,
-      "step": 600
-    },
-    {
-      "epoch": 2.459016393442623,
-      "eval_loss": 0.5126457214355469,
-      "eval_runtime": 199.6781,
-      "eval_samples_per_second": 4.347,
-      "eval_steps_per_second": 0.546,
-      "step": 600
-    },
-    {
-      "epoch": 2.8688524590163933,
-      "grad_norm": 0.23801229894161224,
-      "learning_rate": 4.599860978031383e-06,
-      "loss": 0.5239,
-      "step": 700
     }
   ],
   "logging_steps": 100,
@@ -109,7 +80,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.34827040065536e+18,
+  "total_flos": 7.36870224949248e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null