Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c874995beeada42c622c91704ee0d77ebed455fd00efd2e2ec7aee690f655d0
+oid sha256:998cbc9ef08e0a627bc29f9f011a7ee4f5672cdf6e23f5ac8299fc3c304733e6
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba2c4f8d89034e0320864bbf7841a75afbe0c4ae74d232d2d2b68cd958dcc027
+oid sha256:fa19c21b311253e401d572a7190f6df9402d2cdf026d08b44ee7e99ada846753
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:657a6cb66e4f58198fc327c1f5133fbb8d616a0268932e839b49274c68e14bc1
+oid sha256:565feabc8e9df19644e9a835e978e619bd252ea0fb0a810c0af241484c8da459
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2248de37d2320ddbb576171cc6b8d719f7febfba0a31c5797625bd8cfe79c5ab
+oid sha256:b06606e40b3f01ec7202acbfd1d0145e551b0842ff237681a6bdde0b316ef9b5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4727272727272727,
+  "epoch": 0.7090909090909091,
   "eval_steps": 13,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -87,6 +87,49 @@
       "eval_samples_per_second": 9.97,
       "eval_steps_per_second": 1.286,
       "step": 26
+    },
+    {
+      "epoch": 0.4909090909090909,
+      "grad_norm": 0.45883774757385254,
+      "learning_rate": 9.640574942595196e-05,
+      "loss": 0.4867,
+      "step": 27
+    },
+    {
+      "epoch": 0.5454545454545454,
+      "grad_norm": 0.546485185623169,
+      "learning_rate": 9.504844339512095e-05,
+      "loss": 0.4773,
+      "step": 30
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.5516665577888489,
+      "learning_rate": 9.348705665778478e-05,
+      "loss": 0.4846,
+      "step": 33
+    },
+    {
+      "epoch": 0.6545454545454545,
+      "grad_norm": 0.5257235765457153,
+      "learning_rate": 9.172866268606513e-05,
+      "loss": 0.4445,
+      "step": 36
+    },
+    {
+      "epoch": 0.7090909090909091,
+      "grad_norm": 0.5515545010566711,
+      "learning_rate": 8.978122744408906e-05,
+      "loss": 0.4303,
+      "step": 39
+    },
+    {
+      "epoch": 0.7090909090909091,
+      "eval_loss": 0.41172003746032715,
+      "eval_runtime": 9.3482,
+      "eval_samples_per_second": 9.948,
+      "eval_steps_per_second": 1.284,
+      "step": 39
     }
   ],
   "logging_steps": 3,
@@ -106,7 +149,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.920915796577485e+16,
+  "total_flos": 8.711665917257318e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null