Training in progress, step 140, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:058f12df8fdc50c32a197f5f5c952f739fe65ac649ff7a369a57bd28761b307a
+oid sha256:184e18cfcd9552369bf51740f68926e3162f9bdbb01d2b69fbb0ec79edd52a45
 size 847599616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75e7be1ace81f748a01dd0da135950b137996dc9c206f8885eb59fc7fbceefd6
+oid sha256:971f78334d57716402776ec08101e08f7885ef96295540a7de3ac17f04991f8b
 size 350603

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:443907af357cccf92496cdd4e04b21f17558d4acf38fddc732c70cd7db47e70d
+oid sha256:bfad5b1db434a4570e357f1971d87bf80fdc19c2e91af8a74bce9bbf251a95cc
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc32de04bd8951ded22e38a3a317dcc3e3d6e420820aadb0c1fc7777161631b4
+oid sha256:c40d5e94eed411043d006187ef3d57f655338dfd7cfaaf34e38342dbbae53acc
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6,
+  "epoch": 0.7,
   "eval_steps": 20,
-  "global_step": 120,
+  "global_step": 140,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -230,6 +230,43 @@
       "eval_samples_per_second": 356.77,
       "eval_steps_per_second": 59.581,
       "step": 120
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 0.5889272093772888,
+      "learning_rate": 1.3819660112501052e-06,
+      "loss": 20.15807647705078,
+      "step": 125
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.5750179886817932,
+      "learning_rate": 1.227001661415096e-06,
+      "loss": 20.040406799316408,
+      "step": 130
+    },
+    {
+      "epoch": 0.675,
+      "grad_norm": 0.719745934009552,
+      "learning_rate": 1.0773176740426246e-06,
+      "loss": 20.01085662841797,
+      "step": 135
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.7709663510322571,
+      "learning_rate": 9.339365425440129e-07,
+      "loss": 19.724040222167968,
+      "step": 140
+    },
+    {
+      "epoch": 0.7,
+      "eval_accuracy": 0.07247619047619047,
+      "eval_loss": 9.954747200012207,
+      "eval_runtime": 2.6401,
+      "eval_samples_per_second": 378.767,
+      "eval_steps_per_second": 63.254,
+      "step": 140
     }
   ],
   "logging_steps": 5,