Training in progress, step 45, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5562758958d9c933df9464f619411fbe8ae1fa318035e8e7b577ad7320578083
+oid sha256:d13ab3ed212e21ed52f8f0a92452aa3d61afcea656510bd0bee79af1faf89852
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52122d9880c312c52c04a4ed74ac97875df71512027cc21be7a99f17f5964c1e
+oid sha256:003db3a9356c96106853c72a407f60220caf5ca6154babca4e94b404598b7683
 size 82460660

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f57a98a96269463c4f3b5283c3eb0ad90dcda650b9e164cba692d068abf2b1bc
+oid sha256:d610764392ac240f248e060bc3ee4289569690c159fa277ffe5813b3bbe106d8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc389ed2ec8a0148b9b29024154a8f2f11c6a7454ef1d0724563562d03a46e01
+oid sha256:9776c8df8be516beee92201f32f4a3f5d90539bf47f8ef27e1636cdc132a851e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.017558834288501402,
+  "epoch": 0.021948542860626752,
   "eval_steps": 9,
-  "global_step": 36,
+  "global_step": 45,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -131,6 +131,35 @@
       "eval_samples_per_second": 12.157,
       "eval_steps_per_second": 1.521,
       "step": 36
+    },
+    {
+      "epoch": 0.01902207047920985,
+      "grad_norm": 0.3428895175457001,
+      "learning_rate": 3.824798160583012e-05,
+      "loss": 0.7474,
+      "step": 39
+    },
+    {
+      "epoch": 0.020485306669918303,
+      "grad_norm": 0.5276553630828857,
+      "learning_rate": 3.5959278669726935e-05,
+      "loss": 0.8486,
+      "step": 42
+    },
+    {
+      "epoch": 0.021948542860626752,
+      "grad_norm": 0.45164918899536133,
+      "learning_rate": 3.355050358314172e-05,
+      "loss": 0.7817,
+      "step": 45
+    },
+    {
+      "epoch": 0.021948542860626752,
+      "eval_loss": 0.7856877446174622,
+      "eval_runtime": 284.5888,
+      "eval_samples_per_second": 12.133,
+      "eval_steps_per_second": 1.518,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -150,7 +179,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.802021154612838e+16,
+  "total_flos": 7.339906279931904e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null