Training in progress, step 170, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1313627e57f50b000f77a18dc14176b975cb6869558c43f866b9b1c2e8eb7115
+oid sha256:8d96cf5df8387a45ab1b175187a9f26bc043e803c8bb1d8c17007c49a7bcd82d
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:172f779c9438b79e3c86227407df67a2b35a9df322198efd751e21975aae1ded
+oid sha256:4e847f0a9aae8832c8e1bd08ae0e13ce8582dd32aeeb5c1e5da6d5913c813d12
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6728ffdf9bf59bf13703e6ecc746855ce34369dd62dc3ca69a894e5a32ceaccd
+oid sha256:82e3dacf2b05874132bf6fb4325d351a4ab2ba13cd877561594093394c8a7acc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9d255475980828d00dffcac4a69741da74c7e5ef4f645ab21d69e57306e3317
+oid sha256:963abeacc51d2fd967b0d854376103780952d47675257465be60a3612cecb103
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08068952869979827,
+  "epoch": 0.08313466593312549,
   "eval_steps": 34,
-  "global_step": 165,
+  "global_step": 170,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1202,6 +1202,49 @@
       "learning_rate": 2.0198277271976052e-05,
       "loss": 1.0459,
       "step": 165
+    },
+    {
+      "epoch": 0.08117855614646372,
+      "grad_norm": 1.1469403505325317,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.9885,
+      "step": 166
+    },
+    {
+      "epoch": 0.08166758359312916,
+      "grad_norm": 1.1436965465545654,
+      "learning_rate": 1.8025951709277898e-05,
+      "loss": 0.9769,
+      "step": 167
+    },
+    {
+      "epoch": 0.0821566110397946,
+      "grad_norm": 1.0451879501342773,
+      "learning_rate": 1.6981596918444953e-05,
+      "loss": 1.0134,
+      "step": 168
+    },
+    {
+      "epoch": 0.08264563848646005,
+      "grad_norm": 1.125041127204895,
+      "learning_rate": 1.5965592836210743e-05,
+      "loss": 0.9923,
+      "step": 169
+    },
+    {
+      "epoch": 0.08313466593312549,
+      "grad_norm": 0.8700924515724182,
+      "learning_rate": 1.4978286427038601e-05,
+      "loss": 0.7571,
+      "step": 170
+    },
+    {
+      "epoch": 0.08313466593312549,
+      "eval_loss": 0.9938088655471802,
+      "eval_runtime": 1314.6112,
+      "eval_samples_per_second": 1.965,
+      "eval_steps_per_second": 0.655,
+      "step": 170
     }
   ],
   "logging_steps": 1,
@@ -1221,7 +1264,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.324274422657843e+17,
+  "total_flos": 7.546222132435354e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null