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:d33f72e9cd5583db0003cff54987aec8e5de9f0ad6d681950c2d55ff0c8dd5a5
+oid sha256:6b6eb0573d60ecfe3a141150a24e4c17baa2511c9625774a2220ac0672cb916d
 size 556856304

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:deb4e1e7fa23801b363a688ba5e7649c3e975e3bd05d985a6468b2d0f79c60b3
+oid sha256:576e65e4366bf5b79ae8bef910f998bb6636bcf6fccd7bfdf28c659d733c355d
 size 21599060

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:830c0717e1a623f4428da5c6215b99cc10f0295b0807586eba37d260994f5fd2
+oid sha256:01ef78f97fdbf4f4d79c928df14622d2a5bd7bccc0a4be9d07392ee5bbaea2cc
 size 14244

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": 0.00020824295010845987,
+  "epoch": 0.0003123644251626898,
   "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": 37.593,
       "eval_steps_per_second": 18.797,
       "step": 6
+    },
+    {
+      "epoch": 0.00024295010845986985,
+      "grad_norm": 2.4121720790863037,
+      "learning_rate": 0.00014,
+      "loss": 4.9644,
+      "step": 7
+    },
+    {
+      "epoch": 0.00027765726681127983,
+      "grad_norm": 2.359161138534546,
+      "learning_rate": 0.00016,
+      "loss": 4.4947,
+      "step": 8
+    },
+    {
+      "epoch": 0.0003123644251626898,
+      "grad_norm": 4.865494251251221,
+      "learning_rate": 0.00018,
+      "loss": 5.1167,
+      "step": 9
+    },
+    {
+      "epoch": 0.0003123644251626898,
+      "eval_loss": 1.2180023193359375,
+      "eval_runtime": 321.3039,
+      "eval_samples_per_second": 37.759,
+      "eval_steps_per_second": 18.879,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 669273056870400.0,
+  "total_flos": 1028395184947200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null