Training in progress, step 17500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2d332cfb3e624505463f0996cd4726aa881ac45a6718d65c42518e12efa0289
+oid sha256:7eae9012d93014c9027053f343471d5a0897862eb73b3aa44b0687fa37eabc56
 size 4523108832

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:385095f8805aa85dbfdf95d4042c63bc1fc764e0150428040d6212cb0452b237
+oid sha256:5eace36f2feb1498de4e674ea457b3390625579e85bed978663b88f5c1282e76
 size 2912179275

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:428aed83766f09a6a2d9ccfb86972eeda646225b3b0cd6accec4a90e4f900161
+oid sha256:a94b1a91810562429d557b8e7351faf37318bcc85fdd6894e29a36576f9f1604
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:771ff7b818682cd826d86a4b120b9ebc0073f7aa31644573c4843a8b04554a85
+oid sha256:a1917c9f69ccf15e380d9f4d351dbf92bf96c11b80c90f99f57a0469639c9d08
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9f59f7539e25acfa9df2c68fda6fd6bdcc4a9fa8f5f2af5cee7ac7b6959f643
+oid sha256:0ed3db87d9ab6acb1ce4ebfafc1e1df3a006d0a11ad32694145d43298254810c
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.000566666666666,
+  "epoch": 8.000766666666667,
   "eval_steps": 500,
-  "global_step": 17000,
+  "global_step": 17500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2388,6 +2388,76 @@
       "learning_rate": 1.223008826103174e-05,
       "loss": 1.37287109375,
       "step": 17000
+    },
+    {
+      "epoch": 3.0024,
+      "grad_norm": 1.8621281385421753,
+      "learning_rate": 1.2151630495653046e-05,
+      "loss": 1.2171533203125,
+      "step": 17050
+    },
+    {
+      "epoch": 3.0040666666666667,
+      "grad_norm": 1.6037293672561646,
+      "learning_rate": 1.2073253489291228e-05,
+      "loss": 1.1620811462402343,
+      "step": 17100
+    },
+    {
+      "epoch": 3.005733333333333,
+      "grad_norm": 1.8049744367599487,
+      "learning_rate": 1.1994959464147432e-05,
+      "loss": 1.1776678466796875,
+      "step": 17150
+    },
+    {
+      "epoch": 3.0074,
+      "grad_norm": 1.7445180416107178,
+      "learning_rate": 1.1916750640070056e-05,
+      "loss": 1.1673489379882813,
+      "step": 17200
+    },
+    {
+      "epoch": 3.0090666666666666,
+      "grad_norm": 1.6527574062347412,
+      "learning_rate": 1.1838629234491833e-05,
+      "loss": 1.1704206848144532,
+      "step": 17250
+    },
+    {
+      "epoch": 3.0107333333333335,
+      "grad_norm": 1.7367023229599,
+      "learning_rate": 1.1760597462366926e-05,
+      "loss": 1.203247299194336,
+      "step": 17300
+    },
+    {
+      "epoch": 3.0124,
+      "grad_norm": 1.7566173076629639,
+      "learning_rate": 1.1682657536108159e-05,
+      "loss": 1.119371337890625,
+      "step": 17350
+    },
+    {
+      "epoch": 3.0140666666666664,
+      "grad_norm": 1.5711489915847778,
+      "learning_rate": 1.160481166552426e-05,
+      "loss": 1.3711380004882812,
+      "step": 17400
+    },
+    {
+      "epoch": 3.0157333333333334,
+      "grad_norm": 1.6498943567276,
+      "learning_rate": 1.1527062057757245e-05,
+      "loss": 1.3604568481445312,
+      "step": 17450
+    },
+    {
+      "epoch": 4.000933333333333,
+      "grad_norm": 1.685180902481079,
+      "learning_rate": 1.14494109172198e-05,
+      "loss": 1.1471074676513673,
+      "step": 17500
     }
   ],
   "logging_steps": 50,
@@ -2407,7 +2477,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.4771415930209403e+18,
+  "total_flos": 1.5247432982037135e+18,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null