Training in progress, epoch 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6dc59b48fb66813ca78955fa135a5b9c5eeb223b35e78585ef359fa563ac2307
+oid sha256:693b8b9493a1341e036fe175f3c242fb0e70d29b2806414ec7f6d0e7af219541
 size 218121344

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbfbdfc4b321b15c27cff0da422d2a53f2a28df1c3baf392c51ed726dc694b44
+oid sha256:f8e052ac635caaca4a903cc21b648c6ca206f956c8750d678b1b4d52b5329dc6
 size 109417018

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83dc8405814a784ea21d72ace0f4b91d221f004666d3673770e299e5a05e8fe9
+oid sha256:2e87811f0f1effcce9b8f93da83987850561a5f540a92a1eae3e98079fa8bf27
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30442933123d7669c460d45164eac302a9648bbc2949627d23d3db5a60c61873
+oid sha256:681b81b0832ded00f66f265bc2327f35108bc92cae631f3148849c5007cbbcc8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 14.0,
+  "epoch": 15.0,
   "eval_steps": 500,
-  "global_step": 21378,
+  "global_step": 22905,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1498,6 +1498,118 @@
       "learning_rate": 6.151797603195739e-05,
       "loss": 0.1316,
       "step": 21300
+    },
+    {
+      "epoch": 14.01440733464309,
+      "grad_norm": 0.38168269395828247,
+      "learning_rate": 6.085219707057257e-05,
+      "loss": 0.126,
+      "step": 21400
+    },
+    {
+      "epoch": 14.079895219384413,
+      "grad_norm": 0.385215699672699,
+      "learning_rate": 6.018641810918775e-05,
+      "loss": 0.1112,
+      "step": 21500
+    },
+    {
+      "epoch": 14.145383104125736,
+      "grad_norm": 0.2507851719856262,
+      "learning_rate": 5.9520639147802933e-05,
+      "loss": 0.1104,
+      "step": 21600
+    },
+    {
+      "epoch": 14.21087098886706,
+      "grad_norm": 0.3379518687725067,
+      "learning_rate": 5.8854860186418116e-05,
+      "loss": 0.117,
+      "step": 21700
+    },
+    {
+      "epoch": 14.276358873608382,
+      "grad_norm": 0.3190099895000458,
+      "learning_rate": 5.818908122503329e-05,
+      "loss": 0.1188,
+      "step": 21800
+    },
+    {
+      "epoch": 14.341846758349705,
+      "grad_norm": 0.4639456570148468,
+      "learning_rate": 5.752330226364847e-05,
+      "loss": 0.1179,
+      "step": 21900
+    },
+    {
+      "epoch": 14.407334643091028,
+      "grad_norm": 0.3332715332508087,
+      "learning_rate": 5.685752330226365e-05,
+      "loss": 0.1167,
+      "step": 22000
+    },
+    {
+      "epoch": 14.472822527832351,
+      "grad_norm": 1.894679307937622,
+      "learning_rate": 5.619174434087883e-05,
+      "loss": 0.1174,
+      "step": 22100
+    },
+    {
+      "epoch": 14.538310412573674,
+      "grad_norm": 0.34946346282958984,
+      "learning_rate": 5.552596537949402e-05,
+      "loss": 0.1185,
+      "step": 22200
+    },
+    {
+      "epoch": 14.603798297314997,
+      "grad_norm": 1.04374098777771,
+      "learning_rate": 5.4860186418109194e-05,
+      "loss": 0.1245,
+      "step": 22300
+    },
+    {
+      "epoch": 14.66928618205632,
+      "grad_norm": 0.311128169298172,
+      "learning_rate": 5.419440745672437e-05,
+      "loss": 0.1291,
+      "step": 22400
+    },
+    {
+      "epoch": 14.734774066797643,
+      "grad_norm": 4.8841962814331055,
+      "learning_rate": 5.352862849533955e-05,
+      "loss": 0.12,
+      "step": 22500
+    },
+    {
+      "epoch": 14.800261951538966,
+      "grad_norm": 0.2752310335636139,
+      "learning_rate": 5.286284953395473e-05,
+      "loss": 0.1203,
+      "step": 22600
+    },
+    {
+      "epoch": 14.865749836280289,
+      "grad_norm": 0.44144880771636963,
+      "learning_rate": 5.2197070572569905e-05,
+      "loss": 0.1212,
+      "step": 22700
+    },
+    {
+      "epoch": 14.931237721021612,
+      "grad_norm": 0.19180706143379211,
+      "learning_rate": 5.153129161118508e-05,
+      "loss": 0.1211,
+      "step": 22800
+    },
+    {
+      "epoch": 14.996725605762935,
+      "grad_norm": 0.24586378037929535,
+      "learning_rate": 5.086551264980027e-05,
+      "loss": 0.1237,
+      "step": 22900
     }
   ],
   "logging_steps": 100,
@@ -1517,7 +1629,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.048737596945203e+16,
+  "total_flos": 8.62364741318738e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null