Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:803bd7abe757b8da617577ef829145de8e4ba8989bc086e0261dc4059d85310e
+oid sha256:6610acd1f154c8c5c60e8ad600a48bb5ff141946090d75b39efff4bd416290f5
 size 125040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb26f60631aff7ab8884c03076ae293f7af1d1cd4ea07a68ee19f691e9ccb80f
+oid sha256:f05e8f7586f0d8cac91e3595af1840e052e3f10a08e41737e12cb5cc08faff39
 size 162868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adc65900b1800458289c8c21bab3eeedd0bb320c47305aa0de9c35ef282f5293
+oid sha256:1f0301aae68db5017871275fbfdb6928fd6f7537f55caa23bacf0eda6ec47376
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
+oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.017741385192766974,
+  "epoch": 0.03548277038553395,
   "eval_steps": 10,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,35 @@
       "eval_samples_per_second": 211.247,
       "eval_steps_per_second": 105.965,
       "step": 10
+    },
+    {
+      "epoch": 0.02047082906857728,
+      "grad_norm": 1.2206295728683472,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 44.4605,
+      "step": 15
+    },
+    {
+      "epoch": 0.027294438758103036,
+      "grad_norm": 1.3797295093536377,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 44.4063,
+      "step": 20
+    },
+    {
+      "epoch": 0.027294438758103036,
+      "eval_loss": 11.104840278625488,
+      "eval_runtime": 1.5504,
+      "eval_samples_per_second": 199.298,
+      "eval_steps_per_second": 99.971,
+      "step": 20
+    },
+    {
+      "epoch": 0.03411804844762879,
+      "grad_norm": 1.3237910270690918,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 44.4212,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 125382426624.0,
+  "total_flos": 250764853248.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null