Training in progress, step 4, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cee9f276284ca7c25c07f7c37960e3436a4a84419152567398592e5a80e89cd4
+oid sha256:a3d45e593f157f3e6aee658c2c959fef4c7b25194d0a332658fa2582a678bda1
 size 108113968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13af2221efa72a7db68ca160e1f00de85d2c15ec75c2774788a9e0fb2bcbed04
+oid sha256:fb4cbf3f2b1f025c1f7762addb3b3eb5d4722f9aab735a18e43c46907861a659
 size 55549892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ff1a5a76862bbee56a9275ee6a5621dff6f0928cd044fcf7d46b0f5941256ac
+oid sha256:b8d6b9a0e9e9502751def1097143074ef257eab24506a0f12d159e188fa21987
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60f8f27a9d76e31d3721bb37f2f4c76e866b8dedf8d4315f175dac906a4a966d
+oid sha256:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0008847600088476001,
+  "epoch": 0.0017695200176952002,
   "eval_steps": 2,
-  "global_step": 2,
+  "global_step": 4,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,28 @@
       "eval_samples_per_second": 33.307,
       "eval_steps_per_second": 16.653,
       "step": 2
+    },
+    {
+      "epoch": 0.0013271400132714001,
+      "grad_norm": 20.907835006713867,
+      "learning_rate": 3e-05,
+      "loss": 12.2457,
+      "step": 3
+    },
+    {
+      "epoch": 0.0017695200176952002,
+      "grad_norm": 21.05040740966797,
+      "learning_rate": 4e-05,
+      "loss": 11.8695,
+      "step": 4
+    },
+    {
+      "epoch": 0.0017695200176952002,
+      "eval_loss": 11.01419734954834,
+      "eval_runtime": 114.3529,
+      "eval_samples_per_second": 33.3,
+      "eval_steps_per_second": 16.65,
+      "step": 4
     }
   ],
   "logging_steps": 1,
@@ -56,7 +78,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1641914893860864.0,
+  "total_flos": 3283829787721728.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null