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:d96e088ccbc842d57066219d2b2d4e30b65fb33a8647d9802f367c164ab50e60
+oid sha256:44d5a69b5f1ebda02e68939c126da3a9a8f77b44605b71c2dbbed7798f40079d
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14ff6b4424293da067e38405a10e42a5ffb2a63e81ee976450e11a4dcb7c5429
+oid sha256:82208daa56a18be13aa6cebc801f4c1c58d43a3670299a2b8be630a1655cdd97
 size 64219860

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": 0.00288704438830747,
+  "epoch": 0.00577408877661494,
   "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": 4.811,
       "eval_steps_per_second": 2.407,
       "step": 2
+    },
+    {
+      "epoch": 0.004330566582461205,
+      "grad_norm": 6.875201225280762,
+      "learning_rate": 3e-05,
+      "loss": 22.7572,
+      "step": 3
+    },
+    {
+      "epoch": 0.00577408877661494,
+      "grad_norm": 6.780890464782715,
+      "learning_rate": 4e-05,
+      "loss": 22.3612,
+      "step": 4
+    },
+    {
+      "epoch": 0.00577408877661494,
+      "eval_loss": NaN,
+      "eval_runtime": 241.9135,
+      "eval_samples_per_second": 4.824,
+      "eval_steps_per_second": 2.414,
+      "step": 4
     }
   ],
   "logging_steps": 1,
@@ -56,7 +78,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5065958888570880.0,
+  "total_flos": 1.013191777714176e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null