Training in progress, step 100, checkpoint

last-checkpoint/model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9e33d86b7643ca1dcb0ff586538eca0faa1c5ceb646f55ab91b4c3f84b9791f
+oid sha256:2fe6bcaf9f616919347ffeee8a71be2fb613c9f71c6a3338c5b732ffb1e8b2d6
 size 4943178720

last-checkpoint/model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09671ff7f4231f95a58974cee08101fdbd61e0e44a2da6afaa3f08be535bc56c
+oid sha256:2236db48c00b99ae5863de2038fabe22d15c5054f2785ede9e8fbb3d1c8613ac
 size 4999819336

last-checkpoint/model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:867e8292011b488643369bc98aece5a8d9682c4d0825739096988e70f10694e1
+oid sha256:d6ce91b33fc26f5c6807cbf06b0ccf52b9de474b4f39f114b6b15e2346cfeab5
 size 4540532728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea5954872831a1199bf6baadd994d97241ff683269e1fa383981e05c79f3d256
+oid sha256:6cd02223f419f1c86c6fe67014fc5228d9155b553579c6923475086c41a1c388
 size 14710155092

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d608751b30705d9fdab765f269290cd17ed21a1697e9fcb49bf7ebeaac38aebb
+oid sha256:1f60241cb6cb86cf9966e8cfe2248be00bce643b5808e2c3b78c9cb618eea253
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e84ec92ba6fcaca80f594e6a478d1a67e74e4c4df966b365126aa5fced1503ad
+oid sha256:2e76feebe960d60536ad1ed0bcaee2e12a3f8432f33b7ee3b0cae559b12130c0
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff2e96f7570e4637dff53935f12387cbc820714a50eb737472244c44d20994b4
+oid sha256:2f5988c600823ef881ed3900c9909420e69870efab70abf3dca0673a3c88b057
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67a7f9fde521312c299d8fef03e73900bbba79d87446cea5f97a33fc79bebea8
+oid sha256:7090a3c6759641db81e3ee589636615551bb1b7ce0948f2fd4ab7d7beb35de9c
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b5bd1b09d58ee3e65553e6f9772dc7c5ca98238b1cade33cccd500df2328864
+oid sha256:d429d3d3635edcf38935f000b0d1f4e5db465042c289fb4623c33dce588231ab
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.47619047619047616,
+  "epoch": 0.9523809523809523,
   "eval_steps": 100,
-  "global_step": 50,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -50,6 +50,49 @@
       "learning_rate": 0.00019939306773179497,
       "loss": 8.555,
       "step": 50
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 54.75,
+      "learning_rate": 0.00019863613034027224,
+      "loss": 9.2629,
+      "step": 60
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 38.0,
+      "learning_rate": 0.00019757963826274357,
+      "loss": 16.9373,
+      "step": 70
+    },
+    {
+      "epoch": 0.7619047619047619,
+      "grad_norm": 346.0,
+      "learning_rate": 0.00019622680003092503,
+      "loss": 13.7525,
+      "step": 80
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 18.875,
+      "learning_rate": 0.00019458172417006347,
+      "loss": 10.6593,
+      "step": 90
+    },
+    {
+      "epoch": 0.9523809523809523,
+      "grad_norm": 17.625,
+      "learning_rate": 0.00019264940672148018,
+      "loss": 10.0689,
+      "step": 100
+    },
+    {
+      "epoch": 0.9523809523809523,
+      "eval_loss": 10.551448822021484,
+      "eval_runtime": 26.9779,
+      "eval_samples_per_second": 55.638,
+      "eval_steps_per_second": 6.969,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -69,7 +112,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.495035542700032e+16,
+  "total_flos": 6.990071085400064e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null