Training in progress, step 44, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f903671aaba7f5151211a03597ce7c3e139812a5a63b812828c0ee7ac303762
+oid sha256:33b4844caefd469fc402ef51d94e4a7e03f93da8b31752639992a7762a880a8f
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc3f0cb288820144cea6947f580a632814dee531ee94bc546775718c42085746
+oid sha256:faffbce5868eeb6ddbc3cd65903a3be5ddb7763cc936364e13936bddd04132c3
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:183523c0f84bcb5b8b4b0d5dee6822dc6570a5da2635f659d919d0274e8fe059
+oid sha256:7c027f738a4dfd52c6913eec1699a4b97c1baecedcd1dcbe2a0d7d12892180c4
 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": 0.016886543535620052,
+  "epoch": 0.01857519788918206,
   "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": 8.39,
       "eval_steps_per_second": 8.39,
       "step": 40
+    },
+    {
+      "epoch": 0.017308707124010555,
+      "grad_norm": 3.010507345199585,
+      "learning_rate": 2.3959403439996907e-05,
+      "loss": 0.3272,
+      "step": 41
+    },
+    {
+      "epoch": 0.017730870712401054,
+      "grad_norm": 2.1966700553894043,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.3737,
+      "step": 42
+    },
+    {
+      "epoch": 0.018153034300791557,
+      "grad_norm": 1.8249499797821045,
+      "learning_rate": 1.4735983564590783e-05,
+      "loss": 0.236,
+      "step": 43
+    },
+    {
+      "epoch": 0.01857519788918206,
+      "grad_norm": 2.0696208477020264,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.2272,
+      "step": 44
+    },
+    {
+      "epoch": 0.01857519788918206,
+      "eval_loss": 0.27388355135917664,
+      "eval_runtime": 59.4525,
+      "eval_samples_per_second": 8.393,
+      "eval_steps_per_second": 8.393,
+      "step": 44
     }
   ],
   "logging_steps": 1,
@@ -394,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.483774567120896e+16,
+  "total_flos": 1.6321520238329856e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null