Training in progress, step 182500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f576c297c0eae7ededb3822e0fd97b204d6a332ff9c3b8d7ccd818ebf391761
+oid sha256:e2baaeb2b23d09e31adf3ef5585f3e6639b56c07f476dcaafc27f4ae5d87b820
 size 891644712

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e4dd6b31039b01a958cd2e90946071f91e4689e9d9aca8c7e434cc905cde9ca
+oid sha256:31c9234b22f8508a6d0d4122d44d2c6d1d2e6e2fee5b0b2e55791454aea923e8
 size 1783444357

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9e95bfd6b2f51d2614c1dceffb80aed647095f9f81402665bc8a637aab51a24
+oid sha256:823c43fb8cb66b96b5deeb2005d1b02ad22bf7e9aa812aa31a158370b966082c
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:207898f141fbde837147332552977457f374b23313c4b963d8a62a4e111187ed
+oid sha256:82e2c4a62066e0491348b34524e07a98c2175669eb301b7705f9a7c6d9af8189
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.1424,
+  "epoch": 1.168,
   "eval_steps": 500,
-  "global_step": 178500,
+  "global_step": 182500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2506,6 +2506,62 @@
       "learning_rate": 2.14504e-05,
       "loss": 0.2671,
       "step": 178500
+    },
+    {
+      "epoch": 1.1456,
+      "grad_norm": 0.5736916661262512,
+      "learning_rate": 2.13704e-05,
+      "loss": 0.2648,
+      "step": 179000
+    },
+    {
+      "epoch": 1.1488,
+      "grad_norm": 0.588550329208374,
+      "learning_rate": 2.129056e-05,
+      "loss": 0.2641,
+      "step": 179500
+    },
+    {
+      "epoch": 1.152,
+      "grad_norm": 0.5504462122917175,
+      "learning_rate": 2.121056e-05,
+      "loss": 0.2643,
+      "step": 180000
+    },
+    {
+      "epoch": 1.1552,
+      "grad_norm": 0.5439949035644531,
+      "learning_rate": 2.113056e-05,
+      "loss": 0.2639,
+      "step": 180500
+    },
+    {
+      "epoch": 1.1584,
+      "grad_norm": 0.6882042288780212,
+      "learning_rate": 2.105056e-05,
+      "loss": 0.2595,
+      "step": 181000
+    },
+    {
+      "epoch": 1.1616,
+      "grad_norm": 0.6735561490058899,
+      "learning_rate": 2.097056e-05,
+      "loss": 0.2624,
+      "step": 181500
+    },
+    {
+      "epoch": 1.1648,
+      "grad_norm": 0.5545785427093506,
+      "learning_rate": 2.089056e-05,
+      "loss": 0.2625,
+      "step": 182000
+    },
+    {
+      "epoch": 1.168,
+      "grad_norm": 0.6497994065284729,
+      "learning_rate": 2.081056e-05,
+      "loss": 0.2611,
+      "step": 182500
     }
   ],
   "logging_steps": 500,
@@ -2525,7 +2581,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.6959186771968e+17,
+  "total_flos": 8.890785202176e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null