Training in progress, epoch 3, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1930ad667d0122e05a71ef5e91508c33ec592b0697e7d72b226946cfe1d4672
+oid sha256:31338e02301b1f33b5d3d732981f58ca2697aa137d7e6ae1828e54eb8a73270a
 size 2695611744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42a04278b310b24beef9ff8be29f09cf7bf12e301e84d98e37ad82389e834fb6
+oid sha256:d9dc754447aa59916035ea47878e51d4eda3eff52e6a75c5bf7214699d0cfdf6
 size 26261260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d15855cc66c2961c5cc037b181eb659abb2ac26d92d4c28480e27683e47e34e
+oid sha256:49a66bbd279eb4ab0a90bcfec226c4b910506d73ea2bdc06576ad77b7202ecee
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e8b7bfccb9c07860bceffabef3a52060cc451a19d3abd90d284c09f7120dba6
+oid sha256:541d8b16c337fd96e05a077a2be76d2de8216d931de0afb127b2cab79028732a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.0,
+  "epoch": 3.0,
   "eval_steps": 10,
-  "global_step": 258,
+  "global_step": 387,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -357,6 +357,188 @@
       "eval_samples_per_second": 22.018,
       "eval_steps_per_second": 5.505,
       "step": 250
+    },
+    {
+      "epoch": 2.015617374328941,
+      "grad_norm": 287152.59375,
+      "learning_rate": 7.96875e-05,
+      "loss": 2647.9721,
+      "step": 260
+    },
+    {
+      "epoch": 2.015617374328941,
+      "eval_runtime": 19.5051,
+      "eval_samples_per_second": 22.148,
+      "eval_steps_per_second": 5.537,
+      "step": 260
+    },
+    {
+      "epoch": 2.0937042459736457,
+      "grad_norm": 227855.6875,
+      "learning_rate": 7.890625000000001e-05,
+      "loss": 2429.9967,
+      "step": 270
+    },
+    {
+      "epoch": 2.0937042459736457,
+      "eval_runtime": 19.5753,
+      "eval_samples_per_second": 22.069,
+      "eval_steps_per_second": 5.517,
+      "step": 270
+    },
+    {
+      "epoch": 2.1717911176183504,
+      "grad_norm": 180075.734375,
+      "learning_rate": 7.8125e-05,
+      "loss": 2353.5262,
+      "step": 280
+    },
+    {
+      "epoch": 2.1717911176183504,
+      "eval_runtime": 19.6192,
+      "eval_samples_per_second": 22.019,
+      "eval_steps_per_second": 5.505,
+      "step": 280
+    },
+    {
+      "epoch": 2.249877989263055,
+      "grad_norm": 374717.40625,
+      "learning_rate": 7.734375e-05,
+      "loss": 2223.9002,
+      "step": 290
+    },
+    {
+      "epoch": 2.249877989263055,
+      "eval_runtime": 19.6086,
+      "eval_samples_per_second": 22.031,
+      "eval_steps_per_second": 5.508,
+      "step": 290
+    },
+    {
+      "epoch": 2.32796486090776,
+      "grad_norm": 302520.9375,
+      "learning_rate": 7.65625e-05,
+      "loss": 1899.2279,
+      "step": 300
+    },
+    {
+      "epoch": 2.32796486090776,
+      "eval_runtime": 19.6274,
+      "eval_samples_per_second": 22.01,
+      "eval_steps_per_second": 5.503,
+      "step": 300
+    },
+    {
+      "epoch": 2.4060517325524646,
+      "grad_norm": 178822.03125,
+      "learning_rate": 7.578125e-05,
+      "loss": 1682.3375,
+      "step": 310
+    },
+    {
+      "epoch": 2.4060517325524646,
+      "eval_runtime": 19.6223,
+      "eval_samples_per_second": 22.016,
+      "eval_steps_per_second": 5.504,
+      "step": 310
+    },
+    {
+      "epoch": 2.4841386041971694,
+      "grad_norm": 495346.4375,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 2398.752,
+      "step": 320
+    },
+    {
+      "epoch": 2.4841386041971694,
+      "eval_runtime": 19.5967,
+      "eval_samples_per_second": 22.044,
+      "eval_steps_per_second": 5.511,
+      "step": 320
+    },
+    {
+      "epoch": 2.562225475841874,
+      "grad_norm": 389064.15625,
+      "learning_rate": 7.421875e-05,
+      "loss": 3152.5979,
+      "step": 330
+    },
+    {
+      "epoch": 2.562225475841874,
+      "eval_runtime": 19.613,
+      "eval_samples_per_second": 22.026,
+      "eval_steps_per_second": 5.507,
+      "step": 330
+    },
+    {
+      "epoch": 2.640312347486579,
+      "grad_norm": 364833.375,
+      "learning_rate": 7.34375e-05,
+      "loss": 2780.8895,
+      "step": 340
+    },
+    {
+      "epoch": 2.640312347486579,
+      "eval_runtime": 19.6058,
+      "eval_samples_per_second": 22.034,
+      "eval_steps_per_second": 5.509,
+      "step": 340
+    },
+    {
+      "epoch": 2.7183992191312836,
+      "grad_norm": 250624.234375,
+      "learning_rate": 7.265625000000001e-05,
+      "loss": 2240.6416,
+      "step": 350
+    },
+    {
+      "epoch": 2.7183992191312836,
+      "eval_runtime": 19.6306,
+      "eval_samples_per_second": 22.006,
+      "eval_steps_per_second": 5.502,
+      "step": 350
+    },
+    {
+      "epoch": 2.7964860907759883,
+      "grad_norm": 355084.1875,
+      "learning_rate": 7.1875e-05,
+      "loss": 1683.0152,
+      "step": 360
+    },
+    {
+      "epoch": 2.7964860907759883,
+      "eval_runtime": 19.6274,
+      "eval_samples_per_second": 22.01,
+      "eval_steps_per_second": 5.503,
+      "step": 360
+    },
+    {
+      "epoch": 2.874572962420693,
+      "grad_norm": 408760.53125,
+      "learning_rate": 7.109375e-05,
+      "loss": 1970.6135,
+      "step": 370
+    },
+    {
+      "epoch": 2.874572962420693,
+      "eval_runtime": 19.6037,
+      "eval_samples_per_second": 22.037,
+      "eval_steps_per_second": 5.509,
+      "step": 370
+    },
+    {
+      "epoch": 2.952659834065398,
+      "grad_norm": 253820.046875,
+      "learning_rate": 7.031250000000001e-05,
+      "loss": 2003.0234,
+      "step": 380
+    },
+    {
+      "epoch": 2.952659834065398,
+      "eval_runtime": 19.6328,
+      "eval_samples_per_second": 22.004,
+      "eval_steps_per_second": 5.501,
+      "step": 380
     }
   ],
   "logging_steps": 10,