Training in progress, step 1300, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f969a0948bed2c651ee0376e2b9530983d42d8fddce6465c47996fa8342abda
+oid sha256:0bf7eede2c0f441c39c73721f8eea4ac4a9ec03d59061124d3dd5609631233af
 size 355970836

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca285aebd9342dc71d9a519550a808d80031aa6d14950f0a951d219847fda494
+oid sha256:8447e053424c0e0cc6a81dcab5f337ff796f160b012afda0fab232e4585dcc6b
 size 712036922

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57a98fbdae072481cd4a04e4dba40aca5dd72de7f8f116f374b919687e01043f
+oid sha256:14826f87a6d1f4597dc64c05441ab4b32976806d7c9394950c23908c00ccd88c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de12a84c16ca7d4d35cb56d57baea7004d86cd548bee0fcca8eb591e1f605582
+oid sha256:81cbdfee13cde875628c2c67c528d4aa034fcb58929907fe962e81ec278cbe24
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.024414202199185556,
+  "epoch": 0.026448719049117688,
   "eval_steps": 500,
-  "global_step": 1200,
+  "global_step": 1300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -847,6 +847,76 @@
       "learning_rate": 3.1234716720210725e-06,
       "loss": 192.2185,
       "step": 1200
+    },
+    {
+      "epoch": 0.02461765388417877,
+      "grad_norm": 1015843.75,
+      "learning_rate": 3.123426731137647e-06,
+      "loss": 209.0567,
+      "step": 1210
+    },
+    {
+      "epoch": 0.024821105569171983,
+      "grad_norm": 274952.09375,
+      "learning_rate": 3.123381139377551e-06,
+      "loss": 203.7306,
+      "step": 1220
+    },
+    {
+      "epoch": 0.025024557254165195,
+      "grad_norm": 1192346.875,
+      "learning_rate": 3.1233348967597942e-06,
+      "loss": 196.9537,
+      "step": 1230
+    },
+    {
+      "epoch": 0.02522800893915841,
+      "grad_norm": 300915.9375,
+      "learning_rate": 3.123288003303661e-06,
+      "loss": 194.9343,
+      "step": 1240
+    },
+    {
+      "epoch": 0.025431460624151622,
+      "grad_norm": 371443.53125,
+      "learning_rate": 3.123240459028703e-06,
+      "loss": 198.7411,
+      "step": 1250
+    },
+    {
+      "epoch": 0.025634912309144834,
+      "grad_norm": 224521.265625,
+      "learning_rate": 3.1231922639547463e-06,
+      "loss": 201.7991,
+      "step": 1260
+    },
+    {
+      "epoch": 0.02583836399413805,
+      "grad_norm": 1233164.625,
+      "learning_rate": 3.1231434181018874e-06,
+      "loss": 222.2058,
+      "step": 1270
+    },
+    {
+      "epoch": 0.02604181567913126,
+      "grad_norm": 190394.28125,
+      "learning_rate": 3.123093921490494e-06,
+      "loss": 211.7859,
+      "step": 1280
+    },
+    {
+      "epoch": 0.026245267364124473,
+      "grad_norm": 369118.59375,
+      "learning_rate": 3.1230437741412052e-06,
+      "loss": 181.8996,
+      "step": 1290
+    },
+    {
+      "epoch": 0.026448719049117688,
+      "grad_norm": 1282949.5,
+      "learning_rate": 3.122992976074931e-06,
+      "loss": 200.6364,
+      "step": 1300
     }
   ],
   "logging_steps": 10,