Training in progress, step 63, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:926ebdfc9654db7fbd361e45b0c4a71f2bb3cb80092497d15f3be55330b07082
+oid sha256:06a288d66f41ae1cab29cb7af52be5371834ad3f32f4eabfe3e0cf09b1846a08
 size 228140600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f041f526f6f6b0af90e071f7f7d946f34f1a795dcb7e65de7bbd514c3638607c
+oid sha256:9eed9294f5bcb676d69a7f7204ed2a39ae8754693599ccf55dddaa1ee3961ad1
 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": 6.802,
       "eval_steps_per_second": 0.861,
       "step": 54
+    },
+    {
+      "epoch": 0.1958762886597938,
+      "grad_norm": 1.9179588556289673,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 2.9697,
+      "step": 57
+    },
+    {
+      "epoch": 0.20618556701030927,
+      "grad_norm": 2.107278823852539,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 3.0271,
+      "step": 60
+    },
+    {
+      "epoch": 0.21649484536082475,
+      "grad_norm": 1.985304832458496,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 2.799,
+      "step": 63
+    },
+    {
+      "epoch": 0.21649484536082475,
+      "eval_loss": 0.7117459177970886,
+      "eval_runtime": 71.9674,
+      "eval_samples_per_second": 6.809,
+      "eval_steps_per_second": 0.862,
+      "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