Training in progress, step 99, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de917f814dbdb867628c08292e9d8aa5025ffcaaa8ebcbcd2ca3438f6f169fae
+oid sha256:5137010882493e0d34bd7985edee2b96ef44c5c7dda873c7300e6cc92dae38a5
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a521ee7e0ef65b8c9c597f7360aac471893420b7c34cac1854227cde295038a
+oid sha256:99e0526f6ebca50c1f3909d6fa0c93989b51153b35ccf3125ce2e5af421b40da
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b1a95e9bd92d1040211b3273128d7ca9b48e309b30bde25b9fc65eda7d2b000
+oid sha256:5166d10b0a5d330ee2342d50607a4411c5bbe38bb159437e03cc668fb8d119f7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0569f9f06b6a114946825bdc699040cc55958cfef46aba8eb5fb625896d49025
+oid sha256:5b64833e2721bfb57dae2a544bde34ace02492c2f80bfbff48034c9946dc6b4a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.12418075198344257,
+  "epoch": 0.1365988271817868,
   "eval_steps": 9,
-  "global_step": 90,
+  "global_step": 99,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -305,6 +305,35 @@
       "eval_samples_per_second": 7.131,
       "eval_steps_per_second": 0.894,
       "step": 90
+    },
+    {
+      "epoch": 0.12832011038289065,
+      "grad_norm": 3.2692079544067383,
+      "learning_rate": 7.426068431000882e-07,
+      "loss": 0.85,
+      "step": 93
+    },
+    {
+      "epoch": 0.13245946878233875,
+      "grad_norm": 3.3666374683380127,
+      "learning_rate": 2.4329828146074095e-07,
+      "loss": 0.6383,
+      "step": 96
+    },
+    {
+      "epoch": 0.1365988271817868,
+      "grad_norm": 3.0570571422576904,
+      "learning_rate": 1.522932452260595e-08,
+      "loss": 0.689,
+      "step": 99
+    },
+    {
+      "epoch": 0.1365988271817868,
+      "eval_loss": 0.1600174754858017,
+      "eval_runtime": 171.0652,
+      "eval_samples_per_second": 7.138,
+      "eval_steps_per_second": 0.894,
+      "step": 99
     }
   ],
   "logging_steps": 3,
@@ -324,7 +353,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.5312661952528384e+17,
+  "total_flos": 2.7843928147781222e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null