Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c2e848244af448da7a2d1c4d9688540c28184d38e92e64d11021ca90e6fd714
+oid sha256:4fc8f9f9fb33ad10ebea974fc37d0ba1a177d6603b9d9487788440cdf3e2031b
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62ccce0b864bfcc116927a7d35e1852218b269730b1fc38a2343123aaf954741
+oid sha256:da9d5b0c3cbc91cd33520030a0bf872c9c12222a227f3391ae41adebad173e6e
 size 168037178

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce8441b6f44f4e2fa1d2c030527340ac0218aae059aebad5b78181cb84cf26fe
+oid sha256:d79213b91105086d030b1e0778fbe7d6283f4c083ba909b2ec62c9e7ab91b108
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc75c68691d11d10bcc57bd372463d3e0df9a0caca3bec2a2287a78f782bdcb7
+oid sha256:b610e79daca538339e134160174e96c554fad20f4a4463e6c489c0e388d47d5e
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01576872536136662,
+  "epoch": 0.023653088042049936,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 14.239,
       "eval_steps_per_second": 7.164,
       "step": 6
+    },
+    {
+      "epoch": 0.018396846254927726,
+      "grad_norm": 1.9601093530654907,
+      "learning_rate": 0.00014,
+      "loss": 3.2528,
+      "step": 7
+    },
+    {
+      "epoch": 0.02102496714848883,
+      "grad_norm": 1.72002375125885,
+      "learning_rate": 0.00016,
+      "loss": 2.8813,
+      "step": 8
+    },
+    {
+      "epoch": 0.023653088042049936,
+      "grad_norm": 1.4412205219268799,
+      "learning_rate": 0.00018,
+      "loss": 2.7633,
+      "step": 9
+    },
+    {
+      "epoch": 0.023653088042049936,
+      "eval_loss": 3.0437607765197754,
+      "eval_runtime": 11.297,
+      "eval_samples_per_second": 14.252,
+      "eval_steps_per_second": 7.17,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2219477097775104.0,
+  "total_flos": 3329215646662656.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null