Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4598f274ba3439596734388d7d5de22910d08f43a97dc59de4b057731d42d3d7
+oid sha256:90db6f7523257cea8034b331d2e099960a6ae4b7c656d63dba11bcd490841f89
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bb1aaccc5b5cff853a91bdb2a9e3707ebc01d7a54f42f5466e291129846789e
+oid sha256:ea0b2a565948281537a525addfa5a45bdfce4f07d92bf0efe30dffd3c187c5d3
 size 111142

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd0aaedb551c4ed6d1a681a74f25d0e7f09df1298892466b2d9d6f1f8889fb30
+oid sha256:3b6aa6d92613d8ec55613881281a6c881897813d14e7c601a64ba4f3be3d2a35
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90f7a57653bcfdeb8d3e27706e79cc5f6e1f14bbd0ff72a8e33edaaa89ef8274
+oid sha256:7f7d03f1dba06dbe949e0b7294b5a80e81e1c97413b12e930c7d1d62b4e569ba
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.31733594515181196,
+  "epoch": 0.3525954946131244,
   "eval_steps": 9,
-  "global_step": 81,
+  "global_step": 90,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -276,6 +276,35 @@
       "eval_samples_per_second": 574.788,
       "eval_steps_per_second": 72.183,
       "step": 81
+    },
+    {
+      "epoch": 0.32908912830558273,
+      "grad_norm": 0.04585767164826393,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 10.3658,
+      "step": 84
+    },
+    {
+      "epoch": 0.34084231145935356,
+      "grad_norm": 0.05678807944059372,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 10.367,
+      "step": 87
+    },
+    {
+      "epoch": 0.3525954946131244,
+      "grad_norm": 0.056517504155635834,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 10.3663,
+      "step": 90
+    },
+    {
+      "epoch": 0.3525954946131244,
+      "eval_loss": 10.365554809570312,
+      "eval_runtime": 0.754,
+      "eval_samples_per_second": 570.3,
+      "eval_steps_per_second": 71.619,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -295,7 +324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8472996347904.0,
+  "total_flos": 9414440386560.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null