Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05d5efd167090ec8bc3c99a0757d9e32dc2fd2aa1ecd7b974561723b60ae8d8c
+oid sha256:34a9258aa86967b6c6a8e183260b166bd1c846041e283f5401e6c19494dcd4b2
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:499b0ca08dbdf8408b6e8f764b41a098c964f4a432aca4c97825fd93882f512f
+oid sha256:ca4eb13f8c572709df9d88588ad447e6b80b69dd3305cbeca3982b1a1179ad02
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05531349f6e2487143a7251afc8a645033108171aa1d481234785012b46d00ef
+oid sha256:e7b14d0c915e2c4063f110f3dbec036a026b529b8820509b2913f154771be18b
 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": 0.0001248335552596538,
+  "epoch": 0.0002496671105193076,
   "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": 17.493,
       "eval_steps_per_second": 8.747,
       "step": 3
+    },
+    {
+      "epoch": 0.00016644474034620507,
+      "grad_norm": 5.123037815093994,
+      "learning_rate": 8e-05,
+      "loss": 3.1748,
+      "step": 4
+    },
+    {
+      "epoch": 0.00020805592543275632,
+      "grad_norm": 6.092409133911133,
+      "learning_rate": 0.0001,
+      "loss": 3.4404,
+      "step": 5
+    },
+    {
+      "epoch": 0.0002496671105193076,
+      "grad_norm": 6.741403102874756,
+      "learning_rate": 0.00012,
+      "loss": 3.6998,
+      "step": 6
+    },
+    {
+      "epoch": 0.0002496671105193076,
+      "eval_loss": 0.7651312351226807,
+      "eval_runtime": 578.7606,
+      "eval_samples_per_second": 17.484,
+      "eval_steps_per_second": 8.743,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1051602475548672.0,
+  "total_flos": 2103204951097344.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null