Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee56cf94f87a3df3eaa65c7b5809bca850e994a70fdb6607f7175bd58b370f92
+oid sha256:4efc3fa969a94caa3473e6204335a87e537b245e7d44fb7341a4d18d6c22a57c
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:614633c1671cdf7f917d970a40e7845eecd3f0e5f1075d3dbff988245db9be88
+oid sha256:66025db80e18cb7334a4a6f5169384cdcf63a6b133da71429b5d0ecb85704196
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0ee036ff0ee84b856bf170bd29b04fc3f19ca29270e9b6b9cc560ad52ca9320
+oid sha256:f7701f88edd66004d4466bf636029979f849065c394232d4daaa3f0dc50a5728
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0005251411316791387,
+  "epoch": 0.0010502822633582775,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 9.279,
       "eval_steps_per_second": 4.639,
       "step": 3
+    },
+    {
+      "epoch": 0.0007001881755721851,
+      "grad_norm": 1.4432563781738281,
+      "learning_rate": 8e-05,
+      "loss": 7.782,
+      "step": 4
+    },
+    {
+      "epoch": 0.0008752352194652313,
+      "grad_norm": 1.888183832168579,
+      "learning_rate": 0.0001,
+      "loss": 6.0493,
+      "step": 5
+    },
+    {
+      "epoch": 0.0010502822633582775,
+      "grad_norm": 1.234459638595581,
+      "learning_rate": 0.00012,
+      "loss": 6.7613,
+      "step": 6
+    },
+    {
+      "epoch": 0.0010502822633582775,
+      "eval_loss": 1.7166799306869507,
+      "eval_runtime": 259.3631,
+      "eval_samples_per_second": 9.277,
+      "eval_steps_per_second": 4.638,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 651499696816128.0,
+  "total_flos": 1384436855734272.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null