Training in progress, step 54, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5370294eccd835e415b06aca1329f3ba95203ce6abc5d1b91fd296554fab045c
+oid sha256:d722dda6d4c27c38d1b03df55f7aa2d95ddbd131398b851fa3730a4784a75a6c
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26e297718164d7ba553e6ac0308791bfbaf5385318430d91c6a3c8aedb31ad21
+oid sha256:e9338d702b3601fabaf1eb02fd918e9cc36f21fd23f109f95806d65c9a277a75
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bb89f519660885eea9b51fea75f75a0333612dcf1d1635b7f07fb4145227be2
+oid sha256:6c86ed2e98149a94180ccd60746097fdd11e85131d94438acd3eae90135e8703
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e917c3eea1680bab35c1f582cbc388a7464296952762325512c323f5f76cc5cb
+oid sha256:f449418676ee143dc49fe68c0605204371c150076b291ef62a6b7b955efd8f73
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.021350413664264746,
+  "epoch": 0.025620496397117692,
   "eval_steps": 9,
-  "global_step": 45,
+  "global_step": 54,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -160,6 +160,35 @@
       "eval_samples_per_second": 10.537,
       "eval_steps_per_second": 5.269,
       "step": 45
+    },
+    {
+      "epoch": 0.02277377457521573,
+      "grad_norm": 10.934300422668457,
+      "learning_rate": 0.00014539904997395468,
+      "loss": 21.4568,
+      "step": 48
+    },
+    {
+      "epoch": 0.024197135486166713,
+      "grad_norm": 10.668505668640137,
+      "learning_rate": 0.0001346117057077493,
+      "loss": 21.2971,
+      "step": 51
+    },
+    {
+      "epoch": 0.025620496397117692,
+      "grad_norm": 10.522425651550293,
+      "learning_rate": 0.00012334453638559057,
+      "loss": 22.4085,
+      "step": 54
+    },
+    {
+      "epoch": 0.025620496397117692,
+      "eval_loss": 0.6808061003684998,
+      "eval_runtime": 674.5537,
+      "eval_samples_per_second": 10.525,
+      "eval_steps_per_second": 5.263,
+      "step": 54
     }
   ],
   "logging_steps": 3,
@@ -179,7 +208,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.373171030093988e+17,
+  "total_flos": 2.848133930161275e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null