Training in progress, step 63, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08e7a772fffbe39953ba7a09d7a7b67658a7270839bd36ec5ac27479b5639b12
+oid sha256:580d7e0d1ed9b4bf07c8e75352831c40812274fee0e336067391f9aab808ce03
 size 228140600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4918fb1a7830f002ccf75390e31a833069f5784f5af03a06f52eb71514e71ecc
+oid sha256:6b3124f4c9d93c473ea3c3ca22b7d9b318297c829070ed3e6c06791f8f90c765
 size 116472340

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d856b9ed3ab969ab9e0a41ec549a4535cca2f0c11ca2cfa13f51d67e2e3b244b
+oid sha256:76a9f89e960cac0452a77d3db9f5d20ff25daffc7df7f340fe51556fcbd9bfed
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2011b1e019073e4bafc29de9703ff0a6e7c1252c3a53d804807bd1c99d390d1c
+oid sha256:e53b95eff99f2334cbf7ed4c962db83cb42e931305982518e928382563b5670d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.18556701030927836,
+  "epoch": 0.21649484536082475,
   "eval_steps": 9,
-  "global_step": 54,
+  "global_step": 63,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -189,6 +189,35 @@
       "eval_samples_per_second": 6.833,
       "eval_steps_per_second": 0.865,
       "step": 54
+    },
+    {
+      "epoch": 0.1958762886597938,
+      "grad_norm": 1.945418119430542,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 2.9707,
+      "step": 57
+    },
+    {
+      "epoch": 0.20618556701030927,
+      "grad_norm": 2.055152416229248,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 3.0264,
+      "step": 60
+    },
+    {
+      "epoch": 0.21649484536082475,
+      "grad_norm": 1.9689520597457886,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 2.7934,
+      "step": 63
+    },
+    {
+      "epoch": 0.21649484536082475,
+      "eval_loss": 0.7113768458366394,
+      "eval_runtime": 71.6776,
+      "eval_samples_per_second": 6.836,
+      "eval_steps_per_second": 0.865,
+      "step": 63
     }
   ],
   "logging_steps": 3,
@@ -208,7 +237,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.8641335841980416e+17,
+  "total_flos": 2.1900710513737728e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null