Training in progress, step 44, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f23294f8b89cf6925e8d59776d5a66dd2d4c6da2ed4d25863a2dd3fe47b031c5
+oid sha256:acd42f7e277ea73eeb24cc6785874493fb6203372e9dd599b99b055b24f1fc82
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5904f1110d6059c1226c28dec7c4e85eeb3cc24651b9e84f3a948758f7ec1fe9
+oid sha256:145390c4ddf1514f3d6f2263d50fd0fafdb2f5af12a8c48fe4f855769caf212c
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce9f59fd5c03d0708261ef0e7af3053978f1a8a6c1d8fb67d92ba701dee6b3ec
+oid sha256:809ae7b7c0b89bf58347a7c2b39be06ead95e77ac55e0c214b98278e7ce66603
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c792918044964431737f4cb39f3769dbfd230048b1125ac69a6439eb6c8534b
+oid sha256:7ed6431293c03d1e193e9501dc8ed4f4955bf079fba7f2c1c309a3efed166e50
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.10767160161507403,
+  "epoch": 0.11843876177658143,
   "eval_steps": 4,
-  "global_step": 40,
+  "global_step": 44,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -375,6 +375,42 @@
       "eval_samples_per_second": 7.808,
       "eval_steps_per_second": 7.808,
       "step": 40
+    },
+    {
+      "epoch": 0.11036339165545088,
+      "grad_norm": 0.9937801957130432,
+      "learning_rate": 2.3959403439996907e-05,
+      "loss": 0.2871,
+      "step": 41
+    },
+    {
+      "epoch": 0.11305518169582772,
+      "grad_norm": 1.202613115310669,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.3097,
+      "step": 42
+    },
+    {
+      "epoch": 0.11574697173620457,
+      "grad_norm": 0.7323685884475708,
+      "learning_rate": 1.4735983564590783e-05,
+      "loss": 0.2534,
+      "step": 43
+    },
+    {
+      "epoch": 0.11843876177658143,
+      "grad_norm": 1.1680642366409302,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.2693,
+      "step": 44
+    },
+    {
+      "epoch": 0.11843876177658143,
+      "eval_loss": 0.26846635341644287,
+      "eval_runtime": 10.1072,
+      "eval_samples_per_second": 7.816,
+      "eval_steps_per_second": 7.816,
+      "step": 44
     }
   ],
   "logging_steps": 1,
@@ -394,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.62287843278848e+16,
+  "total_flos": 1.7805294805450752e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null