Training in progress, step 72, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f69ee46466115c3aa5976056f5f684fb09e0586e6b20ed023fda33bb3fa4924
+oid sha256:38aae61d720bcb4cf43470141153a21f5872191fcf1ea25715694f7367fc8b7d
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08ef07e82396a3319d98148f1b585a6e89cf4ae834b265d27851afa9c9362797
+oid sha256:5ca4f43ca6c7532e0831909a064e4084728aa4fc54fd61069af969163261e47d
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bca9d5256ca625bcee2f28acd6eb38730c79c50ea8f7d5ae3c2ca2f208eeaf24
+oid sha256:801b59349ff27e2152b81e7c111e29dc27bc52dce67aadf3d0217d951efa22e7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03b2d2818ab3151c9ed744a4cb682fe1730b800005846a54cc3da941ac8ce20d
+oid sha256:3f9245597e5014ecf432f2646dbac4f88c26cbc6ab1676ee7be71281b45d826d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.029890579129970642,
+  "epoch": 0.03416066186282359,
   "eval_steps": 9,
-  "global_step": 63,
+  "global_step": 72,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -218,6 +218,35 @@
       "eval_samples_per_second": 10.528,
       "eval_steps_per_second": 5.264,
       "step": 63
+    },
+    {
+      "epoch": 0.031313940040921626,
+      "grad_norm": 10.096047401428223,
+      "learning_rate": 7.66554636144095e-05,
+      "loss": 21.0243,
+      "step": 66
+    },
+    {
+      "epoch": 0.03273730095187261,
+      "grad_norm": 10.614026069641113,
+      "learning_rate": 6.538829429225069e-05,
+      "loss": 22.6279,
+      "step": 69
+    },
+    {
+      "epoch": 0.03416066186282359,
+      "grad_norm": 9.915692329406738,
+      "learning_rate": 5.4600950026045326e-05,
+      "loss": 21.7931,
+      "step": 72
+    },
+    {
+      "epoch": 0.03416066186282359,
+      "eval_loss": 0.6665549278259277,
+      "eval_runtime": 673.4954,
+      "eval_samples_per_second": 10.542,
+      "eval_steps_per_second": 5.271,
+      "step": 72
     }
   ],
   "logging_steps": 3,
@@ -237,7 +266,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.323096830228562e+17,
+  "total_flos": 3.7964162600534016e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null