Training in progress, step 19500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66b6ab3ff42b2cdf0354b7f70bd9a1a4076a91b639655aef18c9e1ddc6f4867c
+oid sha256:505ab1c5a34c51302d4bbe4a328e757e4ed0c5b5a72411048c8f13bbf2635e0c
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fa8b871e21aa935f37782ccd210ed25bd8f9e62b08ef3de2bd22cc4ef35b1df
+oid sha256:a7d32e738e2880d3c24e7619fc2f522beb9e9c3515dd4633aed48a29ef433cf5
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd0f95a80e92c03f24f22ba71db4680031a4c2ab72b3c821c67aa452d49e368d
+oid sha256:93c8742c8826e2530a7b338bfc6b583a37586dd446431d091cb023f04fe4b53a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a24b364686c3a4df0863387bf61d379d6122e40cd9c6c72454e7921c0155ca34
+oid sha256:588932b38df48361d8c321bcc1bc5968dc8111dbf384cded84b91367b4837f6a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.08186879754066467,
   "best_model_checkpoint": "./fine-tuned/checkpoint-19000",
-  "epoch": 1.52,
+  "epoch": 1.56,
   "eval_steps": 500,
-  "global_step": 19000,
+  "global_step": 19500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2971,6 +2971,84 @@
       "eval_samples_per_second": 22.707,
       "eval_steps_per_second": 5.677,
       "step": 19000
+    },
+    {
+      "epoch": 1.524,
+      "grad_norm": 0.09976433962583542,
+      "learning_rate": 7.144800000000001e-06,
+      "loss": 0.0496,
+      "step": 19050
+    },
+    {
+      "epoch": 1.528,
+      "grad_norm": 0.19336478412151337,
+      "learning_rate": 7.0848e-06,
+      "loss": 0.0528,
+      "step": 19100
+    },
+    {
+      "epoch": 1.532,
+      "grad_norm": 0.13555702567100525,
+      "learning_rate": 7.0248e-06,
+      "loss": 0.0559,
+      "step": 19150
+    },
+    {
+      "epoch": 1.536,
+      "grad_norm": 0.2016674280166626,
+      "learning_rate": 6.964800000000001e-06,
+      "loss": 0.0568,
+      "step": 19200
+    },
+    {
+      "epoch": 1.54,
+      "grad_norm": 0.8713797330856323,
+      "learning_rate": 6.9048e-06,
+      "loss": 0.0522,
+      "step": 19250
+    },
+    {
+      "epoch": 1.544,
+      "grad_norm": 0.13156233727931976,
+      "learning_rate": 6.8448e-06,
+      "loss": 0.0557,
+      "step": 19300
+    },
+    {
+      "epoch": 1.548,
+      "grad_norm": 0.1713368147611618,
+      "learning_rate": 6.7848e-06,
+      "loss": 0.0574,
+      "step": 19350
+    },
+    {
+      "epoch": 1.552,
+      "grad_norm": 0.13423492014408112,
+      "learning_rate": 6.7248e-06,
+      "loss": 0.0494,
+      "step": 19400
+    },
+    {
+      "epoch": 1.556,
+      "grad_norm": 0.1513233631849289,
+      "learning_rate": 6.6648e-06,
+      "loss": 0.0528,
+      "step": 19450
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 0.1609751433134079,
+      "learning_rate": 6.606000000000001e-06,
+      "loss": 0.0512,
+      "step": 19500
+    },
+    {
+      "epoch": 1.56,
+      "eval_loss": 0.08218736946582794,
+      "eval_runtime": 88.094,
+      "eval_samples_per_second": 22.703,
+      "eval_steps_per_second": 5.676,
+      "step": 19500
     }
   ],
   "logging_steps": 50,
@@ -2990,7 +3068,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.628079968256e+16,
+  "total_flos": 4.749871546368e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null