Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:039dda47309ad39dea13293dcf82ca9de0239ab54a287806639aea7759583226
+oid sha256:506a3c746c120642c25e78bd09eab5d721bf65a9f62cde1b39f7a3caf52c3826
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17a913f04279b656f4440e8a039d009be8d58cbaf62d1256c9ea76ed4644cb09
+oid sha256:e029e74a5518875243f5b4604bfd21a41413323716845b8dcaaf75d3ac3b7cfd
 size 23159290

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df6d9c5b9d89a72068b271d20d9296bc8be0dbce1d6492e0f490c71a0bfbc736
+oid sha256:d8697bdf7d50e6331c02d71383d80ba5d7f9f1e52b53c54c742f01d011d34a2b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aea67b5da66f242c315a67190bee42ac01d2c7b5f9d79262964d41c22411bb70
+oid sha256:c280c35ea7f6e157820b1b8388da58d9a0c818ad290f4f1a0601847a59a7754b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02577319587628866,
+  "epoch": 0.05154639175257732,
   "eval_steps": 97,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -50,6 +50,41 @@
       "learning_rate": 1e-05,
       "loss": 1.0693,
       "step": 5
+    },
+    {
+      "epoch": 0.030927835051546393,
+      "grad_norm": 1.263604998588562,
+      "learning_rate": 1.2e-05,
+      "loss": 1.1302,
+      "step": 6
+    },
+    {
+      "epoch": 0.03608247422680412,
+      "grad_norm": 0.7817522883415222,
+      "learning_rate": 1.4000000000000001e-05,
+      "loss": 0.9247,
+      "step": 7
+    },
+    {
+      "epoch": 0.041237113402061855,
+      "grad_norm": 0.6655614376068115,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.6942,
+      "step": 8
+    },
+    {
+      "epoch": 0.04639175257731959,
+      "grad_norm": 0.9141671061515808,
+      "learning_rate": 1.8e-05,
+      "loss": 0.8889,
+      "step": 9
+    },
+    {
+      "epoch": 0.05154639175257732,
+      "grad_norm": 0.8002082109451294,
+      "learning_rate": 2e-05,
+      "loss": 0.9334,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -69,7 +104,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1935445139128320.0,
+  "total_flos": 3870890278256640.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null