Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:434e26c7bcff76456437ba696366bf870322c9eeca59a3e50314d56b9b919fb3
+oid sha256:d925bbf8bbf53c730617131e220f1619c6b87b5ae731937d70ce61898141b0f8
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e88a7306c673829eeb9cf4a38a30ad6d52a919f3e9579fe56729a732e7519fa5
+oid sha256:bcc9cba162820bffc643b81afdd36fde66758a4ba5d7185d8b2207e3099a4384
 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": 0.00049063701038515,
+  "epoch": 0.0009812740207703,
   "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": 22.131,
       "eval_steps_per_second": 11.07,
       "step": 3
+    },
+    {
+      "epoch": 0.0006541826805135334,
+      "grad_norm": 1.0044587850570679,
+      "learning_rate": 8e-05,
+      "loss": 3.5739,
+      "step": 4
+    },
+    {
+      "epoch": 0.0008177283506419167,
+      "grad_norm": 0.8661907315254211,
+      "learning_rate": 0.0001,
+      "loss": 3.6415,
+      "step": 5
+    },
+    {
+      "epoch": 0.0009812740207703,
+      "grad_norm": 1.4683250188827515,
+      "learning_rate": 0.00012,
+      "loss": 3.7503,
+      "step": 6
+    },
+    {
+      "epoch": 0.0009812740207703,
+      "eval_loss": 3.750457286834717,
+      "eval_runtime": 116.4592,
+      "eval_samples_per_second": 22.111,
+      "eval_steps_per_second": 11.06,
+      "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