Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:506a3c746c120642c25e78bd09eab5d721bf65a9f62cde1b39f7a3caf52c3826
+oid sha256:87c23945d653a95e9f9eec4da69aa6d15a025c78635bb7b033e61096e0bbef76
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e029e74a5518875243f5b4604bfd21a41413323716845b8dcaaf75d3ac3b7cfd
+oid sha256:d9af056b3575961697b1fe06911e2912e701604ee549c59a995da334040581b0
 size 23159290

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8697bdf7d50e6331c02d71383d80ba5d7f9f1e52b53c54c742f01d011d34a2b
+oid sha256:8710411045096e9927495a73130cdf612ae52767f4d1c5c62b815841ffaa199e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c280c35ea7f6e157820b1b8388da58d9a0c818ad290f4f1a0601847a59a7754b
+oid sha256:88de868c96c0a10245aeff16f0aa4d46e50213f783416c2c0d07e645991cb38e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.05154639175257732,
+  "epoch": 0.07731958762886598,
   "eval_steps": 97,
-  "global_step": 10,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -85,6 +85,41 @@
       "learning_rate": 2e-05,
       "loss": 0.9334,
       "step": 10
+    },
+    {
+      "epoch": 0.05670103092783505,
+      "grad_norm": 1.0407661199569702,
+      "learning_rate": 2.2000000000000003e-05,
+      "loss": 0.9861,
+      "step": 11
+    },
+    {
+      "epoch": 0.061855670103092786,
+      "grad_norm": 0.7072747945785522,
+      "learning_rate": 2.4e-05,
+      "loss": 1.0617,
+      "step": 12
+    },
+    {
+      "epoch": 0.06701030927835051,
+      "grad_norm": 0.6469315886497498,
+      "learning_rate": 2.6000000000000002e-05,
+      "loss": 0.846,
+      "step": 13
+    },
+    {
+      "epoch": 0.07216494845360824,
+      "grad_norm": 0.7403808236122131,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 0.8555,
+      "step": 14
+    },
+    {
+      "epoch": 0.07731958762886598,
+      "grad_norm": 0.7198350429534912,
+      "learning_rate": 3e-05,
+      "loss": 0.9019,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -104,7 +139,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3870890278256640.0,
+  "total_flos": 5806335417384960.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null