Training in progress, step 75000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:579a71fbcf796ed2320b1bfdbc71fc5176b97eb09c34e49378b4d90296c31eb8
+oid sha256:62c522b64bf739d00b582ffd0a643c3efac07a2c50ad5c8217960816597aa1b7
 size 891644712

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cee76ad81de6f6dc048b803ad246fcece9bfd6318e54fcb58440f7a3d549a71
+oid sha256:2ea6b08f3a21ebd27e904f6c480a2e53e645065339857b33fb47d39a33ab84a4
 size 1783444357

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fd0d34d79fa86fd679ccbb446dbdf9eb6966c7696206cc4f31e110f5764bfd7
+oid sha256:9a111aa87150022a7015d18e06b4152718ab7403244bfc3590d03281fc35af0e
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65145316c0b4fb3c5a98c06838fed3bfdbe12f66538cde46484d28c82940a1a3
+oid sha256:6d655df9252eb0df8fffa1d13ade85fbe45fc35430c05ca667845bcc4d9ed179
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4288,
+  "epoch": 0.48,
   "eval_steps": 500,
-  "global_step": 67000,
+  "global_step": 75000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -945,6 +945,118 @@
       "learning_rate": 3.928384e-05,
       "loss": 0.3291,
       "step": 67000
+    },
+    {
+      "epoch": 0.432,
+      "grad_norm": 0.6616542339324951,
+      "learning_rate": 3.920384e-05,
+      "loss": 0.3266,
+      "step": 67500
+    },
+    {
+      "epoch": 0.4352,
+      "grad_norm": 0.5957266092300415,
+      "learning_rate": 3.912384e-05,
+      "loss": 0.32,
+      "step": 68000
+    },
+    {
+      "epoch": 0.4384,
+      "grad_norm": 0.6576407551765442,
+      "learning_rate": 3.904384e-05,
+      "loss": 0.3246,
+      "step": 68500
+    },
+    {
+      "epoch": 0.4416,
+      "grad_norm": 0.6852056384086609,
+      "learning_rate": 3.896416e-05,
+      "loss": 0.3268,
+      "step": 69000
+    },
+    {
+      "epoch": 0.4448,
+      "grad_norm": 0.780893087387085,
+      "learning_rate": 3.888416e-05,
+      "loss": 0.3229,
+      "step": 69500
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 0.6741476655006409,
+      "learning_rate": 3.880416e-05,
+      "loss": 0.3188,
+      "step": 70000
+    },
+    {
+      "epoch": 0.4512,
+      "grad_norm": 0.5919800400733948,
+      "learning_rate": 3.872416e-05,
+      "loss": 0.3208,
+      "step": 70500
+    },
+    {
+      "epoch": 0.4544,
+      "grad_norm": 0.6476633548736572,
+      "learning_rate": 3.864416e-05,
+      "loss": 0.322,
+      "step": 71000
+    },
+    {
+      "epoch": 0.4576,
+      "grad_norm": 0.5667979717254639,
+      "learning_rate": 3.8564159999999996e-05,
+      "loss": 0.3151,
+      "step": 71500
+    },
+    {
+      "epoch": 0.4608,
+      "grad_norm": 0.6126554608345032,
+      "learning_rate": 3.8484160000000004e-05,
+      "loss": 0.3185,
+      "step": 72000
+    },
+    {
+      "epoch": 0.464,
+      "grad_norm": 0.7995546460151672,
+      "learning_rate": 3.840416e-05,
+      "loss": 0.3174,
+      "step": 72500
+    },
+    {
+      "epoch": 0.4672,
+      "grad_norm": 0.5964981317520142,
+      "learning_rate": 3.8324160000000005e-05,
+      "loss": 0.3187,
+      "step": 73000
+    },
+    {
+      "epoch": 0.4704,
+      "grad_norm": 0.7718212008476257,
+      "learning_rate": 3.824416e-05,
+      "loss": 0.3156,
+      "step": 73500
+    },
+    {
+      "epoch": 0.4736,
+      "grad_norm": 0.7086686491966248,
+      "learning_rate": 3.8164320000000005e-05,
+      "loss": 0.3189,
+      "step": 74000
+    },
+    {
+      "epoch": 0.4768,
+      "grad_norm": 0.7988029718399048,
+      "learning_rate": 3.808432e-05,
+      "loss": 0.3151,
+      "step": 74500
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.6092699766159058,
+      "learning_rate": 3.8004320000000006e-05,
+      "loss": 0.3153,
+      "step": 75000
     }
   ],
   "logging_steps": 500,
@@ -964,7 +1076,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.2640142934016e+17,
+  "total_flos": 3.65374734336e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null