Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:834304dc19f63138dca1212dbe149fb3ef5fa1e2ab004327704acbd8b2cd54ed
+oid sha256:a3e20d7f0a36a24c594a3ce12cf066047bd260acc15a33bfb55ed773225a5e11
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f92f70a0010de0c28d8414129e3a5b784f7736d9162f5df280330ee3fc46a7e
+oid sha256:89c404d66e9ab8e0bdf4e1592b9cf5ba00d849b7dd9978c3f2abd84cd4455d9b
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9afd89781a51d597dbea42578ed20dd87af91f24b2c8ed574d84057f40bf94d
+oid sha256:0b03e90faa1967f18f72061550dc7b793bd6230a686d92c6466c314f9d209bd4
 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": 0.0003561960996527088,
+  "epoch": 0.0007123921993054176,
   "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": 14.827,
       "eval_steps_per_second": 7.413,
       "step": 10
+    },
+    {
+      "epoch": 0.00041099549959927936,
+      "grad_norm": 1.6798439025878906,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 1.3597,
+      "step": 15
+    },
+    {
+      "epoch": 0.0005479939994657058,
+      "grad_norm": 1.5783166885375977,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.8251,
+      "step": 20
+    },
+    {
+      "epoch": 0.0005479939994657058,
+      "eval_loss": 0.7624468803405762,
+      "eval_runtime": 1041.0681,
+      "eval_samples_per_second": 14.762,
+      "eval_steps_per_second": 7.381,
+      "step": 20
+    },
+    {
+      "epoch": 0.0006849924993321323,
+      "grad_norm": 1.459263563156128,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.6941,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2450672628793344.0,
+  "total_flos": 4855106151383040.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null