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:cdaf5a864a8e355c3eb685c01f87b00ea9079c5de333cc861e1f2dae44781bd3
+oid sha256:86e63f3d1bd3b0ed3da9fa4d0b9af4e535ea1f8aac5d732da421aed475bd1400
 size 6804608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd29cd2c2850b4df46fec2dd3108bbafc3758727f180b2622b3bf95d52582932
+oid sha256:d1d55489a11504df79570d1149a11d2496702532d1fd2f50147a70ee3590e5b1
 size 3633530

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be82660c411c49ebd3a9926ee0b5968e1f38875f53cfa0f6016473da580909ed
+oid sha256:616dacf53bb8fbe792993ba3437fa1700d6e4e98de7f15a000b196b6dd6aa515
 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": 4.21474105684632e-05,
+  "epoch": 8.42948211369264e-05,
   "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": 71.514,
       "eval_steps_per_second": 35.757,
       "step": 3
+    },
+    {
+      "epoch": 5.61965474246176e-05,
+      "grad_norm": 5.531479835510254,
+      "learning_rate": 8e-05,
+      "loss": 11.6567,
+      "step": 4
+    },
+    {
+      "epoch": 7.0245684280772e-05,
+      "grad_norm": 4.737807273864746,
+      "learning_rate": 0.0001,
+      "loss": 11.0582,
+      "step": 5
+    },
+    {
+      "epoch": 8.42948211369264e-05,
+      "grad_norm": 26.38648223876953,
+      "learning_rate": 0.00012,
+      "loss": 11.8254,
+      "step": 6
+    },
+    {
+      "epoch": 8.42948211369264e-05,
+      "eval_loss": 12.05859088897705,
+      "eval_runtime": 414.2123,
+      "eval_samples_per_second": 72.354,
+      "eval_steps_per_second": 36.177,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 10287795142656.0,
+  "total_flos": 20575590285312.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null