Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a181fea7c1b615e1c7af3c8291eacbafbb82e238e823774343772888a879ef69
+oid sha256:4dd0e1153674bcd55996847a8807c34e63010d48590a3e637a0ebc2c711f1720
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:581e6e610fd55f7e841d3b92ab04bcdee38c6d524fbe589974965d1cc4e3f8d7
+oid sha256:2cbe8a1a6b357a69cc5269a67c718a96d161becd852e8d720989999f1ea09312
 size 42608388

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84d10dea762b1d0b61c7813c99ff5f08b42e98239f65c3b0beb32295a4c1787b
+oid sha256:ecd5dda6211db43329456f947b9bdb53d4ac05d8872017cb96bef25db1267364
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb0a9ae08a837d696210720a364c40061c9c8b036f36570a99f11fe3b8d70f51
+oid sha256:562360b448a53e7366b8643d15ad250a0f706aaefd28e30d76b7f5f4480c7196
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 6.397905424193433e-05,
+  "epoch": 0.00012795810848386865,
   "eval_steps": 13,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,6 +30,21 @@
       "eval_samples_per_second": 37.459,
       "eval_steps_per_second": 18.73,
       "step": 13
+    },
+    {
+      "epoch": 9.842931421836051e-05,
+      "grad_norm": 3.3933048248291016,
+      "learning_rate": 0.0002,
+      "loss": 0.7535,
+      "step": 20
+    },
+    {
+      "epoch": 0.00012795810848386865,
+      "eval_loss": 0.6970112323760986,
+      "eval_runtime": 1148.9757,
+      "eval_samples_per_second": 37.231,
+      "eval_steps_per_second": 18.616,
+      "step": 26
     }
   ],
   "logging_steps": 10,
@@ -49,7 +64,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 364420630315008.0,
+  "total_flos": 716275031998464.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null