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:d6554a5e0f2b1cd4c2c67bee6b4b96a7958c7c8191c718762998223be1555431
+oid sha256:0d98d4f29d81c1c3ca32c085ae0b3bf6f96cfd37e34a375a0ad66f2ba42199ab
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:377652259b4d07a7e098815727482a364e6f748f53c2a314443a4c7a4109f93e
+oid sha256:948d1a2b023cfa6b65e34c9746ce2603d1e288812b3605e14741b574016b1e94
 size 37965300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1b9d1adb49620c0e4587ccba0c344a2646e08e84c0b2ea0c0685700278b00b3
+oid sha256:289733692b08074dec0b283d1382287b84329d63bfd23cc3ebcac9ebd7041565
 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": 0.00011642008246422508,
+  "epoch": 0.00023284016492845016,
   "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": 11.076,
       "eval_steps_per_second": 11.076,
       "step": 3
+    },
+    {
+      "epoch": 0.00015522677661896676,
+      "grad_norm": 1.264121413230896,
+      "learning_rate": 8e-05,
+      "loss": 1.1042,
+      "step": 4
+    },
+    {
+      "epoch": 0.00019403347077370846,
+      "grad_norm": 0.9557339549064636,
+      "learning_rate": 0.0001,
+      "loss": 1.25,
+      "step": 5
+    },
+    {
+      "epoch": 0.00023284016492845016,
+      "grad_norm": 0.6429188847541809,
+      "learning_rate": 0.00012,
+      "loss": 1.2236,
+      "step": 6
+    },
+    {
+      "epoch": 0.00023284016492845016,
+      "eval_loss": 1.3257832527160645,
+      "eval_runtime": 489.9181,
+      "eval_samples_per_second": 11.075,
+      "eval_steps_per_second": 11.075,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 391880651046912.0,
+  "total_flos": 783761302093824.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null