Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13d426e1791ac20ea53b34d01f983b9fb3d4a19847a5d77434f22647d248a88d
+oid sha256:9f50aff06f98dbb1489e94e53e8e155ed14da3f1281f7170ce6fc6857625e17a
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3f5f5e0bf26eeddf8c70e10b1ee22e78a511a09a912e3608931cb09d08052a4
+oid sha256:74936d4495ba704d080266e01575c803a734984e6bc8b527a37004d9950de44c
 size 42608388

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfafb2fcabfd743f0b966035f2f1386bf40aa57da14238cd5ad621698e811216
+oid sha256:98d861c6a390a32db99b32b21fb254f11ccec4040fa92f6643a342e1e89e9da6
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f251cec0ccc898e8cfadbccc5c00390e1a82efab4bb1f4764bab0378ad8080cb
+oid sha256:ee9b46319ea183bdb1ff6aeb8d91de1c0cca6ddeb92ade57ebcc69a8fa1ff6e5
 size 14960

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1bcfe7308e7c5d3329203e43279e1401be263f3656157780ebb701694507e83
+oid sha256:1d4024038f7af0e004b66c02d28c6817f03f07a611fdf206029711baf11d4592
 size 14960

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64f42296a843cba92ff001b316d9b2cb8481f8b499476093dff059f336769e40
+oid sha256:f2a5e71e3e8aa7ac8635fed62601d4dab5448c22faf71fdd95b83793fdedfcc4
 size 14960

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": 0.035004321521175455,
+  "epoch": 0.03889369057908384,
   "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": 118.037,
       "eval_steps_per_second": 3.695,
       "step": 81
+    },
+    {
+      "epoch": 0.036300777873811585,
+      "grad_norm": 0.978691577911377,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.4837,
+      "step": 84
+    },
+    {
+      "epoch": 0.03759723422644771,
+      "grad_norm": 0.992375910282135,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 1.4403,
+      "step": 87
+    },
+    {
+      "epoch": 0.03889369057908384,
+      "grad_norm": 1.0013164281845093,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.4748,
+      "step": 90
+    },
+    {
+      "epoch": 0.03889369057908384,
+      "eval_loss": 1.47517728805542,
+      "eval_runtime": 132.0325,
+      "eval_samples_per_second": 118.069,
+      "eval_steps_per_second": 3.696,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -295,7 +324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.568537191303086e+17,
+  "total_flos": 2.854041921079214e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null