Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b64bba7a25775fd4565c864ab38271a2e92fc69515ca33d4f916d78b1897a8d
+oid sha256:74da00eef20da90360dbdf82b0100a44a98e8ba4a3ad4d754b0d6f5983b2cb32
 size 247944

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56127c9c6ee25fa1bd0c49d4d549cda06457b9d0f1040d14c0bc4c9b02333188
+oid sha256:d0abe9372aab9600296cb01c6219bef6cdd7237b2da403766888872a6f82daf4
 size 263088

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:719020131bf833c90632c6b01b06c5301e1876ba50a1273eb06ec350ba411a1a
+oid sha256:f537d6df07787c716bf4621ea221744763bd88e92a07f95d1fa6f6a06d8ac757
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:562360b448a53e7366b8643d15ad250a0f706aaefd28e30d76b7f5f4480c7196
+oid sha256:e2ff6f184064d83b8d06f27cab522b7fa1e27d3258094d54e6a8c251936b5ccb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.009696065634905836,
+  "epoch": 0.014544098452358755,
   "eval_steps": 13,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -45,6 +45,21 @@
       "eval_samples_per_second": 311.146,
       "eval_steps_per_second": 155.848,
       "step": 26
+    },
+    {
+      "epoch": 0.011187768040275966,
+      "grad_norm": 0.9658546447753906,
+      "learning_rate": 0.0002,
+      "loss": 21.892,
+      "step": 30
+    },
+    {
+      "epoch": 0.014544098452358755,
+      "eval_loss": 10.830048561096191,
+      "eval_runtime": 1.84,
+      "eval_samples_per_second": 307.067,
+      "eval_steps_per_second": 153.805,
+      "step": 39
     }
   ],
   "logging_steps": 10,
@@ -64,7 +79,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 270394195968.0,
+  "total_flos": 405591293952.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null