Training in progress, step 7000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6c581988e145fe28231a5b363482e4cc6aa1c009b42a7cafcee97ebd43f75b8
+oid sha256:3b0338daac15cfc77c983eea6a6122874f95852031cec6efb33fb6843974f909
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0334bff194e682ae1d5a62ead6d631a75270fccfa182f5901d35a528b0fb29db
+oid sha256:eff7218517ca4458c3d29b7230cefb18dfe8c171f0a8309d5494771317c7b329
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84aef586a811d916d5e08d0a9103c7f2c4e17550364204602e5b8c751b16f429
+oid sha256:c8c94fe50942676a4b800b8807f5b832311548d8f2c40eff1078995f3e3f0ab5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c31374bac28c19f30a1c44dbbe9200685351926b09acbd3fd6b855ef898dbb0
+oid sha256:c8e5e69cb9645219d028edd3b028ebf30583f1263680ed0ab467551ed740d562
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.43333333333333335,
+  "epoch": 0.4666666666666667,
   "eval_steps": 500,
-  "global_step": 6500,
+  "global_step": 7000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -462,6 +462,41 @@
       "learning_rate": 1.7112444444444445e-05,
       "loss": 0.0652,
       "step": 6500
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.45798158645629883,
+      "learning_rate": 1.7068000000000003e-05,
+      "loss": 0.0778,
+      "step": 6600
+    },
+    {
+      "epoch": 0.44666666666666666,
+      "grad_norm": 0.24436144530773163,
+      "learning_rate": 1.702355555555556e-05,
+      "loss": 0.0725,
+      "step": 6700
+    },
+    {
+      "epoch": 0.4533333333333333,
+      "grad_norm": 0.2054828256368637,
+      "learning_rate": 1.6979111111111114e-05,
+      "loss": 0.0676,
+      "step": 6800
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.12867185473442078,
+      "learning_rate": 1.693466666666667e-05,
+      "loss": 0.0689,
+      "step": 6900
+    },
+    {
+      "epoch": 0.4666666666666667,
+      "grad_norm": 0.17768052220344543,
+      "learning_rate": 1.6890222222222224e-05,
+      "loss": 0.067,
+      "step": 7000
     }
   ],
   "logging_steps": 100,
@@ -481,7 +516,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.583290515456e+16,
+  "total_flos": 1.705082093568e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null