Training in progress, step 8, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:000b9e5c1a5b151d95a2c2835489094078e06bc1a73ebb062da786b544b01fe9
+oid sha256:7490742c318434f985399c767a1c602f55fb6a0dfe00dcfd110170199aad847e
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b26e69c6c984c95f70ebea58c73dd66f739afbf75f67fd3783796440657cd545
+oid sha256:ae79ea085872aedd87bc5a62cb5c44bd8029427fd8eebd823d147f0676a7f312
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b274d200228065c5ad050511a1f7866a6edb57bdaa953138cf781ba60f5569eb
+oid sha256:d73744cc9da6cf4515a44034b122856d46a3fed397efa1e527493ee573696292
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:917587e2c0a52fd7c3d6680e02e388879c84c249a215f319208d6a9951b36ba9
+oid sha256:26a93b2a1f4b5368650119fe6e0d6eec6d19cda6badeba4d21943ab48964fa00
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0011976944382064525,
+  "epoch": 0.002395388876412905,
   "eval_steps": 4,
-  "global_step": 4,
+  "global_step": 8,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -51,6 +51,42 @@
       "eval_samples_per_second": 8.276,
       "eval_steps_per_second": 8.276,
       "step": 4
+    },
+    {
+      "epoch": 0.0014971180477580657,
+      "grad_norm": 17.0161075592041,
+      "learning_rate": 0.0001,
+      "loss": 10.8734,
+      "step": 5
+    },
+    {
+      "epoch": 0.001796541657309679,
+      "grad_norm": 17.905702590942383,
+      "learning_rate": 0.00012,
+      "loss": 11.8788,
+      "step": 6
+    },
+    {
+      "epoch": 0.002095965266861292,
+      "grad_norm": 21.928312301635742,
+      "learning_rate": 0.00014,
+      "loss": 10.4667,
+      "step": 7
+    },
+    {
+      "epoch": 0.002395388876412905,
+      "grad_norm": 13.790472030639648,
+      "learning_rate": 0.00016,
+      "loss": 9.8745,
+      "step": 8
+    },
+    {
+      "epoch": 0.002395388876412905,
+      "eval_loss": 9.637001037597656,
+      "eval_runtime": 85.1568,
+      "eval_samples_per_second": 8.267,
+      "eval_steps_per_second": 8.267,
+      "step": 8
     }
   ],
   "logging_steps": 1,
@@ -70,7 +106,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1483774567120896.0,
+  "total_flos": 2967549134241792.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null