Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a92ae5e2212751215a5a7797175d922be05437d7435295c7c4747d5b9326612
+oid sha256:d9f669241c53eaa4fb2e42fe8f653ce32487f9d4e365c8a8d44e81375da2ef00
 size 50365768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64f979cc9a7f6e2bc55abdba0480d05e266a308de6f97c16909f0ff1e927c2f8
+oid sha256:fe8561ceff1699750581ddc2ca781f54a73fc8534017b8e87ccb774b0ccfc03d
 size 25859156

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ae53ec2f7c1d85cd228fe8701e5305c2ee78f38f76e12a32bca293ef0b0d296
+oid sha256:f88f964ad87577ca1e97998fb85b6f51001376ab9ef4339f8dfdda15c840d119
 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": 0.00022862804122925678,
+  "epoch": 0.00045725608245851356,
   "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": 34.005,
       "eval_steps_per_second": 17.006,
       "step": 3
+    },
+    {
+      "epoch": 0.00030483738830567567,
+      "grad_norm": 3.0439226627349854,
+      "learning_rate": 8e-05,
+      "loss": 6.9977,
+      "step": 4
+    },
+    {
+      "epoch": 0.00038104673538209464,
+      "grad_norm": 4.791325092315674,
+      "learning_rate": 0.0001,
+      "loss": 7.0244,
+      "step": 5
+    },
+    {
+      "epoch": 0.00045725608245851356,
+      "grad_norm": 4.13270378112793,
+      "learning_rate": 0.00012,
+      "loss": 6.8967,
+      "step": 6
+    },
+    {
+      "epoch": 0.00045725608245851356,
+      "eval_loss": 1.7656927108764648,
+      "eval_runtime": 162.9982,
+      "eval_samples_per_second": 33.896,
+      "eval_steps_per_second": 16.951,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 298334847762432.0,
+  "total_flos": 596669695524864.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null