Training in progress, step 26500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2eb2e99816ec43430cbc064844c5e9639d5777774741cf5128e00d44cc22f84
+oid sha256:1d79b372779eff7f0c6aceb504965064dd1c783ad82104b4d76980d00e49918c
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffff2b04f3ac17f12a961b31f194814499e7fd990021cd2b459a7cd25f837f54
+oid sha256:9c628badd7736af0b2faf987d91b45461eb187ce865defe1587b4f0f12761f4a
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f52f95da495bb27845cab982f10d0992545e1a1f3379ad63ed77c13e8413544
+oid sha256:ca75d61d47f3eab98fc406af0fc3456adbe0767939034d58dea95e5d6ff029b5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34f762ade12141f21b1db11036bc2604582ab540ca56d64f7190f6e92cb5741c
+oid sha256:d82350f62694be97e6ec7d5caa84c96c6ffb8c480e6a50519ae958022a2c0417
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.7333333333333334,
+  "epoch": 1.7666666666666666,
   "eval_steps": 500,
-  "global_step": 26000,
+  "global_step": 26500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1835,6 +1835,41 @@
       "learning_rate": 8.448000000000001e-06,
       "loss": 0.0555,
       "step": 26000
+    },
+    {
+      "epoch": 1.74,
+      "grad_norm": 0.25770798325538635,
+      "learning_rate": 8.403555555555556e-06,
+      "loss": 0.0513,
+      "step": 26100
+    },
+    {
+      "epoch": 1.7466666666666666,
+      "grad_norm": 0.2838607430458069,
+      "learning_rate": 8.359111111111112e-06,
+      "loss": 0.0605,
+      "step": 26200
+    },
+    {
+      "epoch": 1.7533333333333334,
+      "grad_norm": 0.12263695150613785,
+      "learning_rate": 8.314666666666667e-06,
+      "loss": 0.0574,
+      "step": 26300
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.17367112636566162,
+      "learning_rate": 8.270666666666667e-06,
+      "loss": 0.0581,
+      "step": 26400
+    },
+    {
+      "epoch": 1.7666666666666666,
+      "grad_norm": 0.26262718439102173,
+      "learning_rate": 8.226222222222224e-06,
+      "loss": 0.0541,
+      "step": 26500
     }
   ],
   "logging_steps": 100,
@@ -1854,7 +1889,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.333162061824e+16,
+  "total_flos": 6.454953639936e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null