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:a8f0fc7c20ffc9cfd69ed661d9e1e1dae9ebaa9ad752e92860846fa4302c5ea9
+oid sha256:0d52c79f719e9c11583c71b46d7384879fd220f61d6ece2afd7d7df309224eaf
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c24e405533b4e9b216b37b7f54fc83d3779e46afc6329eb312ba1b5ab3c9664
+oid sha256:2fb7eafe90a9330dd1963fa68d3295bf134956cd01d30bee9c868a9c7c6967e7
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a8fbdd40f7edc9d5266c41a92e911a33f810a381088729bf4c84d9fe8f8cfae
+oid sha256:446f86ec2d710de4e25bb65aa3702d3d6d34aaf5102619f692e1fb433a8cb9a7
 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": 0.0006232633027761186,
+  "epoch": 0.0009348949541641779,
   "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": 35.918,
       "eval_steps_per_second": 17.959,
       "step": 6
+    },
+    {
+      "epoch": 0.0007271405199054717,
+      "grad_norm": 1.1893061399459839,
+      "learning_rate": 0.00014,
+      "loss": 1.5154,
+      "step": 7
+    },
+    {
+      "epoch": 0.0008310177370348249,
+      "grad_norm": 1.1050771474838257,
+      "learning_rate": 0.00016,
+      "loss": 1.3836,
+      "step": 8
+    },
+    {
+      "epoch": 0.0009348949541641779,
+      "grad_norm": 1.5559436082839966,
+      "learning_rate": 0.00018,
+      "loss": 1.5296,
+      "step": 9
+    },
+    {
+      "epoch": 0.0009348949541641779,
+      "eval_loss": 1.5618540048599243,
+      "eval_runtime": 114.3143,
+      "eval_samples_per_second": 35.464,
+      "eval_steps_per_second": 17.732,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 312560831692800.0,
+  "total_flos": 462590030905344.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null