Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02f9d08a710e62b5d00f568a054105b05155848d37ade7f3c411ba90d3d3df51
+oid sha256:d840ed2d6725bbd5793a683fc34de318730f9d40072adcd54d1e7b69cf2beb60
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:324626b3c14fea6b3eb3daff41d75d99e5775f6ac26502a13ba4970fdc0d1d2d
+oid sha256:00704fa1000b0f6f458cea94614bdcb9356d5417aad06dc1502a5fdadf41c7c2
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20ae40147066520ba06d8488dffecb1617761bf0f5a71e5b8f891ada27bea484
+oid sha256:fd93ad71d1e4da2e65f4e2c9390e9d7b7bc2ea6079b0f1bd60a10893bb8881fb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d63217b923cb177f669d6bc2174b89abdc6a56d968d279b505491b37976d9bb
+oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.029282576866764276,
+  "epoch": 0.05856515373352855,
   "eval_steps": 5,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,6 +30,28 @@
       "eval_samples_per_second": 15.658,
       "eval_steps_per_second": 1.957,
       "step": 5
+    },
+    {
+      "epoch": 0.03513909224011713,
+      "grad_norm": 23.506786346435547,
+      "learning_rate": 6e-05,
+      "loss": 29.8118,
+      "step": 6
+    },
+    {
+      "epoch": 0.0527086383601757,
+      "grad_norm": 23.666690826416016,
+      "learning_rate": 9e-05,
+      "loss": 21.4367,
+      "step": 9
+    },
+    {
+      "epoch": 0.05856515373352855,
+      "eval_loss": 3.3852756023406982,
+      "eval_runtime": 18.4101,
+      "eval_samples_per_second": 15.644,
+      "eval_steps_per_second": 1.955,
+      "step": 10
     }
   ],
   "logging_steps": 3,
@@ -49,7 +71,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6652543295815680.0,
+  "total_flos": 1.330508659163136e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null