Training in progress, step 45, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bb9a096db4afd4939889cf29b28bce0cd60c204e43b83bde086473e9fa95635
+oid sha256:ca8853fd10c42593ba458a656c81b3bbb1e4dbe03de7fec06fb5938c3a5e3152
 size 191968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f93824adee0ed2d7e519db2a451ec9064b5bb5f6d49be8d009d012c5ec3eda2
+oid sha256:a87bccbafeee423590f7a4a274508d4c30036dbbfee8ca36260c9a7b89a50617
 size 253144

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4faae14a1aa6472da1e35d90c3eeeb0dd65ba4a4be7087c6d32cacd0c607e1b
+oid sha256:1f6aaadfc3a2995ea3bff4c91194faec2c49a54ff830cb39f07c142f67055ad8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd18e5325bf99a4b662a5314e5f491b65903ffc83b0317f63835d8305a50591e
+oid sha256:4ec0bb6efeeb25000ef7426abb9d88265daa212fa2a170e1fb3f58996efa27f6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.09029345372460497,
+  "epoch": 0.10158013544018059,
   "eval_steps": 5,
-  "global_step": 40,
+  "global_step": 45,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -170,6 +170,28 @@
       "eval_samples_per_second": 546.511,
       "eval_steps_per_second": 68.771,
       "step": 40
+    },
+    {
+      "epoch": 0.09480812641083522,
+      "grad_norm": 0.5754713416099548,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 10.3213,
+      "step": 42
+    },
+    {
+      "epoch": 0.10158013544018059,
+      "grad_norm": 0.7273910641670227,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 10.3121,
+      "step": 45
+    },
+    {
+      "epoch": 0.10158013544018059,
+      "eval_loss": 10.314825057983398,
+      "eval_runtime": 1.405,
+      "eval_samples_per_second": 531.663,
+      "eval_steps_per_second": 66.903,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -189,7 +211,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4462026424320.0,
+  "total_flos": 5019779727360.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null