Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ef909cf0c9ad7b5eb1ebf2e04efae99a9a0e143d62d9d72650d5ab2e70b2abf
+oid sha256:256d7b0364ce08d05ce7e7fa030997236dd61c9eeab760c183296bac80be173c
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e82bf9b08ccd30a079819eaf476bcbd437d4d4793751cde4b1bd8a18705d882
+oid sha256:412121c10f738a940c3d1638e6f4d589cdcc31908f3d7530e4a2e16a3644b624
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a6013b3e443f3d3918b66f424386dee8227e6cbe276f00f582fd5eee09d9831
+oid sha256:dc035f9a226a227cf75c9503cec9ab273f9add4d937ca11d5a322e17d720ce7a
 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": 2.1315789473684212,
+  "epoch": 2.3684210526315788,
   "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": 14.032,
       "eval_steps_per_second": 1.754,
       "step": 81
+    },
+    {
+      "epoch": 2.2105263157894735,
+      "grad_norm": 7.461455821990967,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.5446,
+      "step": 84
+    },
+    {
+      "epoch": 2.2894736842105265,
+      "grad_norm": 6.697714328765869,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 1.5799,
+      "step": 87
+    },
+    {
+      "epoch": 2.3684210526315788,
+      "grad_norm": 7.722606182098389,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.5105,
+      "step": 90
+    },
+    {
+      "epoch": 2.3684210526315788,
+      "eval_loss": 0.7937512993812561,
+      "eval_runtime": 4.5625,
+      "eval_samples_per_second": 14.027,
+      "eval_steps_per_second": 1.753,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -295,7 +324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.132918702300201e+17,
+  "total_flos": 1.2594821570179891e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null