Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:625e5c210a36a513977cc0cb1d71e1d7b313fd6260b0ee0862a73dccfe674749
+oid sha256:2c10f37b750403a96ae6084466851348efb7b6b2796c78833911d5d3edcf3f77
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a517aa42654c591f119b91e02582cba9261ddaa1be9c4056e743954a1113c7dd
+oid sha256:b276e14efa049fcfea754e3e072281a628300a5157d431f228eecc371794517e
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cf86cd5b19b8056a2759fc36b0c4f0323fb9c04403c19df65bcd5311b20dea5
+oid sha256:693d65ff7d3abbbb13c7ee57d38fa6e7fa5181ebaaabad321dd22b54929bbad4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0002223539875481767,
+  "epoch": 0.0004447079750963534,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 21.921,
       "eval_steps_per_second": 10.963,
       "step": 3
+    },
+    {
+      "epoch": 0.0002964719833975689,
+      "grad_norm": 0.6753953099250793,
+      "learning_rate": 8e-05,
+      "loss": 2.3004,
+      "step": 4
+    },
+    {
+      "epoch": 0.0003705899792469612,
+      "grad_norm": 0.6175580024719238,
+      "learning_rate": 0.0001,
+      "loss": 2.1341,
+      "step": 5
+    },
+    {
+      "epoch": 0.0004447079750963534,
+      "grad_norm": 1.1478474140167236,
+      "learning_rate": 0.00012,
+      "loss": 1.6489,
+      "step": 6
+    },
+    {
+      "epoch": 0.0004447079750963534,
+      "eval_loss": 1.9228562116622925,
+      "eval_runtime": 259.5731,
+      "eval_samples_per_second": 21.886,
+      "eval_steps_per_second": 10.945,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 949861251809280.0,
+  "total_flos": 1899722503618560.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null