Training in progress, step 36500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61dce64509302181dbd0102d94f8e63119a5e468f1ab30981e6b95a40a16a0f7
+oid sha256:66629fbba7f2d42de83407ccc7c4a7cb20d143079ca2ed45dbc07d04a90a40bf
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8aee7a7bb130bc58eccba7310fd2e1c0ff9bc9a9460551dab2ac36a3c09f233f
+oid sha256:6d02b75121788cccbde8e0ee668a0edad332b5ebb58494b81e48d2fa78f15f7d
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d52b5d54b1b44c26afdd58b8aa610c5f355b531f51747715e0d2588d67b0dd03
+oid sha256:6e9822f3fcdc1597872af5dd87f19db7e35ac92105cd8babdb7bf1d6ea8c5abd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3545c32cd08bfe14c5940277cc90a883188128e319d14e37ac1ae89581718ce4
+oid sha256:e696025a153a4c23b525b445028cbabae1500984cfdb159ce8be1d5922b1b1ea
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.4,
+  "epoch": 2.4333333333333336,
   "eval_steps": 500,
-  "global_step": 36000,
+  "global_step": 36500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2543,6 +2543,41 @@
       "learning_rate": 4.006222222222223e-06,
       "loss": 0.0523,
       "step": 36000
+    },
+    {
+      "epoch": 2.4066666666666667,
+      "grad_norm": 0.1548595130443573,
+      "learning_rate": 3.961777777777778e-06,
+      "loss": 0.0498,
+      "step": 36100
+    },
+    {
+      "epoch": 2.413333333333333,
+      "grad_norm": 0.13865716755390167,
+      "learning_rate": 3.917333333333333e-06,
+      "loss": 0.0522,
+      "step": 36200
+    },
+    {
+      "epoch": 2.42,
+      "grad_norm": 0.20406047999858856,
+      "learning_rate": 3.872888888888889e-06,
+      "loss": 0.0481,
+      "step": 36300
+    },
+    {
+      "epoch": 2.4266666666666667,
+      "grad_norm": 0.20818284153938293,
+      "learning_rate": 3.8284444444444445e-06,
+      "loss": 0.0524,
+      "step": 36400
+    },
+    {
+      "epoch": 2.4333333333333336,
+      "grad_norm": 0.37012940645217896,
+      "learning_rate": 3.7840000000000005e-06,
+      "loss": 0.0445,
+      "step": 36500
     }
   ],
   "logging_steps": 100,
@@ -2562,7 +2597,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.768993624064e+16,
+  "total_flos": 8.890785202176e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null