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:c0dce05b630e9c2e86edbbff79488f358c363bb63689e7c14a6e58d4272ca6db
+oid sha256:ea9a0d070addc1e41df9499859a848e1e0e53048f126996a22c3207fd67ec27a
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dde531e2820073335839e972585c173b4638836d666b4f9292a8913c054a81df
+oid sha256:8ee9f876fc61fe78e5c62f51d3408a88423e9d5fbd6ab7b121a1aa94f1da5d09
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aab3a91804771975540e4b79c14167f2b311d9eae66c6ec29d3118b42dc107f6
+oid sha256:b9924210ab879c904501d7849ac30798dabb2a3e05d515d30a640be5f23f0e2a
 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": 0.021957913998170174,
+  "epoch": 0.03293687099725526,
   "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": 14.743,
       "eval_steps_per_second": 7.435,
       "step": 6
+    },
+    {
+      "epoch": 0.025617566331198535,
+      "grad_norm": 0.4981963634490967,
+      "learning_rate": 0.00014,
+      "loss": 1.9151,
+      "step": 7
+    },
+    {
+      "epoch": 0.0292772186642269,
+      "grad_norm": 0.6484657526016235,
+      "learning_rate": 0.00016,
+      "loss": 2.16,
+      "step": 8
+    },
+    {
+      "epoch": 0.03293687099725526,
+      "grad_norm": 0.5292857885360718,
+      "learning_rate": 0.00018,
+      "loss": 1.8135,
+      "step": 9
+    },
+    {
+      "epoch": 0.03293687099725526,
+      "eval_loss": 1.9987196922302246,
+      "eval_runtime": 7.7857,
+      "eval_samples_per_second": 14.771,
+      "eval_steps_per_second": 7.45,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2295498937466880.0,
+  "total_flos": 3641136245637120.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null