Training in progress, step 81, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8152951bba880b8dd098b43ce8826bfe370c9e18ba810a0e56cf1a0fc2b749d0
+oid sha256:2ada63e5b7945af7375e1b5b10bdc992ec4c6c37df44fcaf5231a5b197915795
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ff9a319a38aa73505193c97e8028755d7d1b27aabc47a6791b4df00ccaabd0a
+oid sha256:291f8e7ff37073b84a86c0c1f1ab2856c66e33cda2b2929565dc65de1b1f4a70
 size 51418196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5678b89d63a8f6afd4f0ee73978dbb937bdfcc02872dacf50efff3a6ade9cee2
+oid sha256:0599d4234737a59a883ed84cbb0eec398ba4dc9db2ac8d6e74985d6bc0634bf1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dcc5b33f65fdaffd6a8f394a182adc55f95c04061e1e53640018b07b2b89f10
+oid sha256:90f7a57653bcfdeb8d3e27706e79cc5f6e1f14bbd0ff72a8e33edaaa89ef8274
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.004146748833726891,
+  "epoch": 0.0046650924379427515,
   "eval_steps": 9,
-  "global_step": 72,
+  "global_step": 81,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -247,6 +247,35 @@
       "eval_samples_per_second": 21.87,
       "eval_steps_per_second": 2.734,
       "step": 72
+    },
+    {
+      "epoch": 0.004319530035132178,
+      "grad_norm": 0.8846902251243591,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 9.9641,
+      "step": 75
+    },
+    {
+      "epoch": 0.004492311236537465,
+      "grad_norm": 1.0415371656417847,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 9.3965,
+      "step": 78
+    },
+    {
+      "epoch": 0.0046650924379427515,
+      "grad_norm": 1.0671367645263672,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 9.7664,
+      "step": 81
+    },
+    {
+      "epoch": 0.0046650924379427515,
+      "eval_loss": 2.4352002143859863,
+      "eval_runtime": 1335.8618,
+      "eval_samples_per_second": 21.891,
+      "eval_steps_per_second": 2.737,
+      "step": 81
     }
   ],
   "logging_steps": 3,
@@ -266,7 +295,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.360486289349018e+16,
+  "total_flos": 6.097322892695962e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null