Training in progress, step 120, checkpoint

last-checkpoint/model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:131319d8a7fe08d319723f8b6d34dfd70b80add9ca5c6339290231d753d14cbb
+oid sha256:e342615652d3355c941cabe26c9bc43ce0cde519ec9909863bd616caa209494f
 size 4956450288

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43727221ce16b1eb20dff7a5bd20c13db6466b8f235c27411438fc465ff009b6
+oid sha256:3615dc2652952bd4d19c155add154fd6d6119ee4cf783e23eb565457600595d3
 size 1214366696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6673752d5cac8d14cf1213bfb598bd645955ce86f0a5a29a1a30d4d87e9f374e
+oid sha256:4b1733a1dcd2eb9346cd1cff3ddea590e71c1d6f957507459bbb9924be90e8df
 size 6269038402

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2f73e2ab92ed2314dc8e34e2c9a86c2bd8f2a48f49f9ce7c42ffccc444e0e9b
+oid sha256:08967576c6a01e2b79ae881c01d2fc6197de21635fde332923b63e77336196b3
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edab11ab9164a8c1e91fde82983060d22f74114a0388c4e5f7d1919ae5183d3e
+oid sha256:700cc977da44e3a561ebdeda2bbe4a20b2d1355120654c3de282f9033096ade5
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1676d02a11ee5a81cb4b9811d1ee8050a6fd51250ad90acc01ba9a7d1ea1295e
+oid sha256:c4235b11ccc186aa417239bf82936738712bddfbfe3de3656f3f1fd123cc7677
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:477127038fa627ccd8cc28b1e1e3eafd4f5ab2572d0d466ae60a5f66ea0ea5f6
+oid sha256:762fb925474c45baaabf6e3ddde1e332c6438ee533dced0d6a0e4774cd278a3d
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:898092e0bf0f6dbc7c89ddc78136fe76ce924561e71751216da91be467d8b5d1
+oid sha256:8f51ee0edceaed552a085478c75fcd8a4c72aa0831c2dde7d467b2ceb3ac7693
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.7027027027027026,
+  "epoch": 3.2432432432432434,
   "eval_steps": 20,
-  "global_step": 100,
+  "global_step": 120,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -125,6 +125,28 @@
       "eval_samples_per_second": 70.756,
       "eval_steps_per_second": 3.583,
       "step": 100
+    },
+    {
+      "epoch": 2.972972972972973,
+      "grad_norm": 1.546875,
+      "learning_rate": 0.00018460952524209355,
+      "loss": 0.626,
+      "step": 110
+    },
+    {
+      "epoch": 3.2432432432432434,
+      "grad_norm": 2.0625,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.3162,
+      "step": 120
+    },
+    {
+      "epoch": 3.2432432432432434,
+      "eval_loss": 2.800004005432129,
+      "eval_runtime": 21.4262,
+      "eval_samples_per_second": 70.054,
+      "eval_steps_per_second": 3.547,
+      "step": 120
     }
   ],
   "logging_steps": 10,
@@ -144,7 +166,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.819283858358272e+16,
+  "total_flos": 8.183140630029926e+16,
   "train_batch_size": 5,
   "trial_name": null,
   "trial_params": null