Training in progress, step 400, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5700ee3c9d1db43f4c0eb47d83e41bb1e6153af7f8aaca330c81e259ef8334cd
+oid sha256:54e70bed0532421328b0a5eae1739faf10554edef780345a7fa3efb4101337ce
 size 4972163696

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f520ba021d87f70182c10c296bbd1c92e39233c1111343590483795a7cf97c3c
+oid sha256:95a346cbc481c36aea80e0ead995296794033e276ef2958ea624b0a8dab087f7
 size 2669366920

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8aca617bbe1e87cb0fad83175890500981250316f530042a5ea6f3973e33e275
-size 7762295162
+oid sha256:9d44dc86a55eac12c7d27ec17997915090f0ea9c93b110f6fad40e221f7532e6
+size 7762295418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02bd6697dd0ac01f79967d93e880e93c5ad7e5d6a672668dd596f9f42c435066
+oid sha256:e91c93adbd867f6b29a746102b970b6b093425427ec88b11aabc9c40173c479b
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1946c0d35865c02655624537450071d8e3a581f1d24f3c539357cae293b3d2d2
+oid sha256:1adfb7aa43d630bdf1ccfdbfef716e32470407c637beab3ddca1f102e2a0250f
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9faf933c304288a566e09316737d2bdccb42e76da4138d98110982bcbf5dbf1
+oid sha256:b80afdcf8c913f6f90c75552c66b7ab16d54b1bc5a68d99f816e671415b3822a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f2cb6de5c0f2b78c1515e90a9ab03144587d336dd27fc87023f09785c5d64cb
+oid sha256:d44d4c0cecc344649d594c1ef688eecfc0ca6ff0fe5583fa3d1db6101db970b6
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cd11d413bc67bf01de9a1a006e9e7655be307353028b25f5b3c299e5b6b7a44
+oid sha256:0e4c78e85c4ba926d25150d4aaddeaf5728dcb066f4afc01202e3e56f29a5487
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.7735849056603774,
+  "epoch": 7.547169811320755,
   "eval_steps": 200,
-  "global_step": 200,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -163,6 +163,154 @@
       "eval_samples_per_second": 79.007,
       "eval_steps_per_second": 4.948,
       "step": 200
+    },
+    {
+      "epoch": 3.9622641509433962,
+      "grad_norm": 0.58984375,
+      "learning_rate": 0.00015469481581224272,
+      "loss": 0.1385,
+      "step": 210
+    },
+    {
+      "epoch": 4.150943396226415,
+      "grad_norm": 0.294921875,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.0523,
+      "step": 220
+    },
+    {
+      "epoch": 4.339622641509434,
+      "grad_norm": 0.3515625,
+      "learning_rate": 0.00014515333583108896,
+      "loss": 0.0338,
+      "step": 230
+    },
+    {
+      "epoch": 4.528301886792453,
+      "grad_norm": 0.337890625,
+      "learning_rate": 0.00014016954246529696,
+      "loss": 0.2872,
+      "step": 240
+    },
+    {
+      "epoch": 4.716981132075472,
+      "grad_norm": 0.3828125,
+      "learning_rate": 0.00013506375551927547,
+      "loss": 0.0379,
+      "step": 250
+    },
+    {
+      "epoch": 4.90566037735849,
+      "grad_norm": 0.33984375,
+      "learning_rate": 0.00012985148110016947,
+      "loss": 0.153,
+      "step": 260
+    },
+    {
+      "epoch": 5.09433962264151,
+      "grad_norm": 0.12451171875,
+      "learning_rate": 0.00012454854871407994,
+      "loss": 0.0279,
+      "step": 270
+    },
+    {
+      "epoch": 5.283018867924528,
+      "grad_norm": 0.1083984375,
+      "learning_rate": 0.00011917106319237386,
+      "loss": 0.0072,
+      "step": 280
+    },
+    {
+      "epoch": 5.471698113207547,
+      "grad_norm": 0.1318359375,
+      "learning_rate": 0.00011373535578184082,
+      "loss": 0.0076,
+      "step": 290
+    },
+    {
+      "epoch": 5.660377358490566,
+      "grad_norm": 0.142578125,
+      "learning_rate": 0.00010825793454723325,
+      "loss": 0.0072,
+      "step": 300
+    },
+    {
+      "epoch": 5.849056603773585,
+      "grad_norm": 0.1396484375,
+      "learning_rate": 0.00010275543423681621,
+      "loss": 0.0078,
+      "step": 310
+    },
+    {
+      "epoch": 6.037735849056604,
+      "grad_norm": 0.138671875,
+      "learning_rate": 9.724456576318381e-05,
+      "loss": 0.0061,
+      "step": 320
+    },
+    {
+      "epoch": 6.226415094339623,
+      "grad_norm": 0.78515625,
+      "learning_rate": 9.174206545276677e-05,
+      "loss": 0.1177,
+      "step": 330
+    },
+    {
+      "epoch": 6.415094339622642,
+      "grad_norm": 0.11962890625,
+      "learning_rate": 8.626464421815919e-05,
+      "loss": 0.0031,
+      "step": 340
+    },
+    {
+      "epoch": 6.60377358490566,
+      "grad_norm": 0.035400390625,
+      "learning_rate": 8.082893680762619e-05,
+      "loss": 0.0028,
+      "step": 350
+    },
+    {
+      "epoch": 6.7924528301886795,
+      "grad_norm": 0.04541015625,
+      "learning_rate": 7.54514512859201e-05,
+      "loss": 0.0026,
+      "step": 360
+    },
+    {
+      "epoch": 6.981132075471698,
+      "grad_norm": 0.0400390625,
+      "learning_rate": 7.014851889983057e-05,
+      "loss": 0.0034,
+      "step": 370
+    },
+    {
+      "epoch": 7.169811320754717,
+      "grad_norm": 0.0225830078125,
+      "learning_rate": 6.493624448072457e-05,
+      "loss": 0.1195,
+      "step": 380
+    },
+    {
+      "epoch": 7.3584905660377355,
+      "grad_norm": 0.034423828125,
+      "learning_rate": 5.983045753470308e-05,
+      "loss": 0.0019,
+      "step": 390
+    },
+    {
+      "epoch": 7.547169811320755,
+      "grad_norm": 0.0263671875,
+      "learning_rate": 5.484666416891109e-05,
+      "loss": 0.0019,
+      "step": 400
+    },
+    {
+      "epoch": 7.547169811320755,
+      "eval_loss": 3.409816265106201,
+      "eval_runtime": 19.0169,
+      "eval_samples_per_second": 78.93,
+      "eval_steps_per_second": 4.943,
+      "step": 400
     }
   ],
   "logging_steps": 10,
@@ -182,7 +330,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.4627987628910182e+17,
+  "total_flos": 2.9246827031166976e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null