Training in progress, step 99, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35b0db7d479601e21e8f0626e67fea9b826f418569abf03d4a42c25218d2bbb0
+oid sha256:d191a4dcdd0d80192d8f379912f43cce9a522db8425cfd2952ee4cb494478eef
 size 15156512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a5f9bb544edbf970e83de407f978f724ad3e44d97dcc88a78ab8d38478e9418
+oid sha256:df5be478806888e3b774e916c357011b36548c74d4ae0b69b4b26edae693e3bb
 size 7825914

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5498bdb9b4323418be388590bc2e68008eff5e39569ec0e9c796f50445383dfc
+oid sha256:daf8e692b7fafb84a783e36d6e835fe74b68e49b97c817b8776a1a850668db12
 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": 0.09049773755656108,
+  "epoch": 0.09954751131221719,
   "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": 150.007,
       "eval_steps_per_second": 18.807,
       "step": 90
+    },
+    {
+      "epoch": 0.09351432880844646,
+      "grad_norm": 2.2963476181030273,
+      "learning_rate": 7.426068431000882e-07,
+      "loss": 4.1301,
+      "step": 93
+    },
+    {
+      "epoch": 0.09653092006033183,
+      "grad_norm": 2.7444159984588623,
+      "learning_rate": 2.4329828146074095e-07,
+      "loss": 4.3495,
+      "step": 96
+    },
+    {
+      "epoch": 0.09954751131221719,
+      "grad_norm": 2.268852472305298,
+      "learning_rate": 1.522932452260595e-08,
+      "loss": 4.1211,
+      "step": 99
+    },
+    {
+      "epoch": 0.09954751131221719,
+      "eval_loss": 4.140535354614258,
+      "eval_runtime": 11.1432,
+      "eval_samples_per_second": 150.315,
+      "eval_steps_per_second": 18.846,
+      "step": 99
     }
   ],
   "logging_steps": 3,
@@ -324,7 +353,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7714123315937280.0,
+  "total_flos": 8485535647531008.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null