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:c1cd6fa7488f5ebec771a8b0b2a5e082550394febfd304442aea6a9b9bd40634
+oid sha256:415a0abaf8a68085419b7e0b6cc0f40eadf4491916718539cd1e1c56b4fafc66
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81bdb4e163aac6881fa8985dbc72e21986d407a42f675b6b78572d02b559d8db
+oid sha256:ef0ff3668c32765c514132e1ab6f462dc70ef5dd076f8d2e8c3392d9f459e0c4
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:baacc8adb5b1f537298b9ceb42d97a30d074c4b147330d0a8447401d9393d584
+oid sha256:838f9faa35d772fe841bd5f559e6f6f7ef19974dd49a11a2f7d21009977548bc
 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": 0.0005170965031348976,
+  "epoch": 0.0007756447547023463,
   "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": 24.907,
       "eval_steps_per_second": 12.454,
       "step": 6
+    },
+    {
+      "epoch": 0.0006032792536573804,
+      "grad_norm": 1.0919623374938965,
+      "learning_rate": 0.00014,
+      "loss": 1.0546,
+      "step": 7
+    },
+    {
+      "epoch": 0.0006894620041798634,
+      "grad_norm": 1.4632925987243652,
+      "learning_rate": 0.00016,
+      "loss": 1.6939,
+      "step": 8
+    },
+    {
+      "epoch": 0.0007756447547023463,
+      "grad_norm": 2.3321034908294678,
+      "learning_rate": 0.00018,
+      "loss": 2.6489,
+      "step": 9
+    },
+    {
+      "epoch": 0.0007756447547023463,
+      "eval_loss": NaN,
+      "eval_runtime": 196.1766,
+      "eval_samples_per_second": 24.906,
+      "eval_steps_per_second": 12.453,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 676540148613120.0,
+  "total_flos": 1025060831232000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null