Training in progress, step 17000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08df383ddf8539b1c156d553a75182fefc1bd9cb8d1be80a3bb2d48549c72268
+oid sha256:ee7142eae13c2e07731af54b545ac51bda5556ea3f592995cf80a6a611f7a001
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4942b168045dd01e1507ab88999a6fa88c39bef7244ce53f7c7f5c00a6c5e0d5
+oid sha256:8599a0264032f7e486689cdb52a108f56cf68a52b701dfa3ff59464f8da7ad06
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac7de248f1039c222833b4241b4257bf2afda51b5d7ba778b660b2c2050b7e97
+oid sha256:c552c5778e7213237c153e06b58720168ca8baccd54cd6b284f96928b35e9241
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c923446f6a9040a7fff312fb9744a6058c7cd7ec45e59a8a878177b2e96073c7
+oid sha256:570514209dc9b87d23b36d54c5948989ae9b03cae5fc9a097914a9ef458ad51f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.08243728429079056,
-  "best_model_checkpoint": "./fine-tuned/checkpoint-15000",
-  "epoch": 1.32,
+  "best_metric": 0.08219126611948013,
+  "best_model_checkpoint": "./fine-tuned/checkpoint-17000",
+  "epoch": 1.3599999999999999,
   "eval_steps": 500,
-  "global_step": 16500,
+  "global_step": 17000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2581,6 +2581,84 @@
       "eval_samples_per_second": 22.705,
       "eval_steps_per_second": 5.676,
       "step": 16500
+    },
+    {
+      "epoch": 1.324,
+      "grad_norm": 0.10573418438434601,
+      "learning_rate": 1.0144800000000002e-05,
+      "loss": 0.058,
+      "step": 16550
+    },
+    {
+      "epoch": 1.328,
+      "grad_norm": 0.1370289921760559,
+      "learning_rate": 1.00848e-05,
+      "loss": 0.0552,
+      "step": 16600
+    },
+    {
+      "epoch": 1.332,
+      "grad_norm": 0.15583133697509766,
+      "learning_rate": 1.0024800000000001e-05,
+      "loss": 0.0505,
+      "step": 16650
+    },
+    {
+      "epoch": 1.336,
+      "grad_norm": 0.12616191804409027,
+      "learning_rate": 9.9648e-06,
+      "loss": 0.0563,
+      "step": 16700
+    },
+    {
+      "epoch": 1.34,
+      "grad_norm": 0.1533484160900116,
+      "learning_rate": 9.9048e-06,
+      "loss": 0.0564,
+      "step": 16750
+    },
+    {
+      "epoch": 1.3439999999999999,
+      "grad_norm": 0.11609365046024323,
+      "learning_rate": 9.844800000000001e-06,
+      "loss": 0.0538,
+      "step": 16800
+    },
+    {
+      "epoch": 1.3479999999999999,
+      "grad_norm": 0.12423556298017502,
+      "learning_rate": 9.7848e-06,
+      "loss": 0.0519,
+      "step": 16850
+    },
+    {
+      "epoch": 1.3519999999999999,
+      "grad_norm": 0.13122333586215973,
+      "learning_rate": 9.7248e-06,
+      "loss": 0.0518,
+      "step": 16900
+    },
+    {
+      "epoch": 1.3559999999999999,
+      "grad_norm": 0.17409804463386536,
+      "learning_rate": 9.664800000000001e-06,
+      "loss": 0.0544,
+      "step": 16950
+    },
+    {
+      "epoch": 1.3599999999999999,
+      "grad_norm": 0.13961808383464813,
+      "learning_rate": 9.6048e-06,
+      "loss": 0.0523,
+      "step": 17000
+    },
+    {
+      "epoch": 1.3599999999999999,
+      "eval_loss": 0.08219126611948013,
+      "eval_runtime": 88.051,
+      "eval_samples_per_second": 22.714,
+      "eval_steps_per_second": 5.679,
+      "step": 17000
     }
   ],
   "logging_steps": 50,
@@ -2600,7 +2678,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.019122077696e+16,
+  "total_flos": 4.140913655808e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null