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:b3a62e7b6af11aec7b06eb56aaeb4b4c3b4c4b3f15be4a996855a9a76711fd9b
+oid sha256:ba34c655bc1124e1736c396082dfe181b44402c6c153cbfa81c5858285581b75
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0f8dc74684b4f8c66be9c8aeadd1b6eec22d36dcd9b0237ca654504cb2edf13
+oid sha256:90ef3e93b3de54b04ecd000aa25fe4407f95761c07cef7445df1c833c7b97fdd
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f3323fe783519afc87d45ddad501fb1901cdb8e5b89fb94a2c86db4ff814d51
+oid sha256:18d4c94e2cd3126bb9a7c65102f0c81057ba2db04d64baf90e527b4a953730fb
 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": 0.07383773928896992,
+  "epoch": 0.0820419325432999,
   "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": 4.521,
       "eval_steps_per_second": 0.565,
       "step": 81
+    },
+    {
+      "epoch": 0.07657247037374658,
+      "grad_norm": 8.541152000427246,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 3.5673,
+      "step": 84
+    },
+    {
+      "epoch": 0.07930720145852324,
+      "grad_norm": 7.397488117218018,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 2.7927,
+      "step": 87
+    },
+    {
+      "epoch": 0.0820419325432999,
+      "grad_norm": 9.43271541595459,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 3.8056,
+      "step": 90
+    },
+    {
+      "epoch": 0.0820419325432999,
+      "eval_loss": 0.8453258872032166,
+      "eval_runtime": 408.7994,
+      "eval_samples_per_second": 4.521,
+      "eval_steps_per_second": 0.565,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -295,7 +324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.148060618471506e+17,
+  "total_flos": 2.3765777055429427e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null