Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27fef8ded5719e8fb5484cd599b4b7131aac140b2d2490477cae80fcfc9ab0a8
+oid sha256:e9208ec33273f291a92a7e5187a418113884ea04afdd9b606a1e4283ba30b04c
 size 692136856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c09c212099541e04bb0ccf809c1acd5254a1915fb52e04db0d0e7fd77ca4545
+oid sha256:67a98e4cd8c25485cf6062731bd7abf44bb9bbc2ae90345c252cb7c1a43c32d4
 size 85723284

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a5e3c19f7b2892f9204c2db9ed620b572aab049411a4232f39c90287c803cca
+oid sha256:5aef72e80bca5ad86c4740cd44eaa6a311a9485d9a446667badbb08fac831b01
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35459df988092e3ff9e3c1b91118d006576bed7e1956fe6101d7671fcd8c5396
+oid sha256:472d41c9b9333a74c9178e69008f711ff75ebcb1c9882a89e4e8e8fceffd9b44
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5adea6def46a60dd5782726d51a89bdf0f30226cd791e511d8af09a5644f99e2
+oid sha256:6e65bdb10468d12c8b6afa89fe8730e38a94a4f704431de04b0c1bf27440afce
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.21202854230377166,
+  "epoch": 0.4240570846075433,
   "eval_steps": 13,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -114,6 +114,105 @@
       "eval_samples_per_second": 10.859,
       "eval_steps_per_second": 2.734,
       "step": 13
+    },
+    {
+      "epoch": 0.22833843017329256,
+      "grad_norm": 0.5429165959358215,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.8139,
+      "step": 14
+    },
+    {
+      "epoch": 0.24464831804281345,
+      "grad_norm": 0.44588130712509155,
+      "learning_rate": 8.296729075500344e-05,
+      "loss": 0.7791,
+      "step": 15
+    },
+    {
+      "epoch": 0.2609582059123344,
+      "grad_norm": 0.4463639259338379,
+      "learning_rate": 8.043807145043604e-05,
+      "loss": 0.8165,
+      "step": 16
+    },
+    {
+      "epoch": 0.27726809378185524,
+      "grad_norm": 0.5119205713272095,
+      "learning_rate": 7.777851165098012e-05,
+      "loss": 0.7869,
+      "step": 17
+    },
+    {
+      "epoch": 0.29357798165137616,
+      "grad_norm": 0.4943891763687134,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.7749,
+      "step": 18
+    },
+    {
+      "epoch": 0.30988786952089703,
+      "grad_norm": 0.41848573088645935,
+      "learning_rate": 7.211443451095007e-05,
+      "loss": 0.8104,
+      "step": 19
+    },
+    {
+      "epoch": 0.32619775739041795,
+      "grad_norm": 0.5443288087844849,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.8394,
+      "step": 20
+    },
+    {
+      "epoch": 0.3425076452599388,
+      "grad_norm": 0.43257173895835876,
+      "learning_rate": 6.607197326515808e-05,
+      "loss": 0.8379,
+      "step": 21
+    },
+    {
+      "epoch": 0.35881753312945974,
+      "grad_norm": 0.5105078220367432,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 0.7741,
+      "step": 22
+    },
+    {
+      "epoch": 0.3751274209989806,
+      "grad_norm": 0.4616767466068268,
+      "learning_rate": 5.9754516100806423e-05,
+      "loss": 0.7985,
+      "step": 23
+    },
+    {
+      "epoch": 0.39143730886850153,
+      "grad_norm": 0.41591593623161316,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 0.7988,
+      "step": 24
+    },
+    {
+      "epoch": 0.4077471967380224,
+      "grad_norm": 0.4813802242279053,
+      "learning_rate": 5.327015646150716e-05,
+      "loss": 0.7526,
+      "step": 25
+    },
+    {
+      "epoch": 0.4240570846075433,
+      "grad_norm": 0.4680293798446655,
+      "learning_rate": 5e-05,
+      "loss": 0.7901,
+      "step": 26
+    },
+    {
+      "epoch": 0.4240570846075433,
+      "eval_loss": 0.7714418172836304,
+      "eval_runtime": 38.5188,
+      "eval_samples_per_second": 10.722,
+      "eval_steps_per_second": 2.7,
+      "step": 26
     }
   ],
   "logging_steps": 1,
@@ -133,7 +232,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.9250203895516365e+17,
+  "total_flos": 5.850040779103273e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null