Training in progress, step 400, checkpoint

last-checkpoint/model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6c319358483ec806c968e4f220fca3000a77c1b4fa2c80a17261bc1f1c497c9
+oid sha256:20a0f0b677ef9523e368a689805afdfe8875ecd90c6960f2f7823eba167a58a8
 size 4939116424

last-checkpoint/model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10b376216017c71cf1c9e6ff0845011a5ed32bb51a3eb9f58a594029349a867e
+oid sha256:8d4a5e123b884f1d254253ae334a454b0856430c5f820dfd3fd9926871d64be2
 size 4947390880

last-checkpoint/model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0cba33d8f86c6783f821adbb981e2a6e28677cfe46e2a24ba93374d75f3d860
+oid sha256:b3e284667793422609e961f4a27500e23a7e5122779d6caa8194042d9faf5898
 size 3590619888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc28acdfb42fca0f2220441d9aa568c85740428b840ce6fe96b7f147d781a8b8
-size 13688025584
+oid sha256:eba62ba6cdbdf56cc308938e5fc68656ba481ae09db1d3bc15a4e944b80c8267
+size 13688025904

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f20d155a14d34cd1bb6d04e5de90f3224906e1758821edd752a8f1a9085a2db
+oid sha256:f31d0e52b1203dc466957ba44cd0260d6bbeb846b199ce38ce109573104799a8
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad18e870a176ca75a54f6620f83de92bdfd5a91302744d90bff8e5feae2fe0c5
+oid sha256:178eb7de4f968298664210c650d8f3dd26a6c7eede0fbd3483a681aa2cf31592
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9009a52be47b75834407dc5e146ed5360e6f23a35bff27bab34ef6fb47df1661
+oid sha256:d7878fc29b8c840af8b2a9ab8ac8eb6299bb984eb570e358e198f23044fb4b47
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fb494a08fd57e7c6f63f06826c872164986e81b271996be0496671f713bdcc3
+oid sha256:31e880d516fe20f9a295381218f40401e9f27b60286de66ce3e10de6e74808cf
 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": 1.8518518518518519,
+  "epoch": 3.7037037037037037,
   "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": 57.512,
       "eval_steps_per_second": 7.203,
       "step": 200
+    },
+    {
+      "epoch": 1.9444444444444444,
+      "grad_norm": 1.21875,
+      "learning_rate": 0.00015469481581224272,
+      "loss": 0.9473,
+      "step": 210
+    },
+    {
+      "epoch": 2.037037037037037,
+      "grad_norm": 1.1015625,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.7034,
+      "step": 220
+    },
+    {
+      "epoch": 2.1296296296296298,
+      "grad_norm": 0.92578125,
+      "learning_rate": 0.00014515333583108896,
+      "loss": 0.2726,
+      "step": 230
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.953125,
+      "learning_rate": 0.00014016954246529696,
+      "loss": 0.2504,
+      "step": 240
+    },
+    {
+      "epoch": 2.314814814814815,
+      "grad_norm": 0.93359375,
+      "learning_rate": 0.00013506375551927547,
+      "loss": 0.2544,
+      "step": 250
+    },
+    {
+      "epoch": 2.4074074074074074,
+      "grad_norm": 0.8359375,
+      "learning_rate": 0.00012985148110016947,
+      "loss": 0.2437,
+      "step": 260
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.796875,
+      "learning_rate": 0.00012454854871407994,
+      "loss": 0.2416,
+      "step": 270
+    },
+    {
+      "epoch": 2.5925925925925926,
+      "grad_norm": 0.84765625,
+      "learning_rate": 0.00011917106319237386,
+      "loss": 0.2402,
+      "step": 280
+    },
+    {
+      "epoch": 2.685185185185185,
+      "grad_norm": 0.8515625,
+      "learning_rate": 0.00011373535578184082,
+      "loss": 0.2521,
+      "step": 290
+    },
+    {
+      "epoch": 2.7777777777777777,
+      "grad_norm": 0.73828125,
+      "learning_rate": 0.00010825793454723325,
+      "loss": 0.2415,
+      "step": 300
+    },
+    {
+      "epoch": 2.8703703703703702,
+      "grad_norm": 0.84375,
+      "learning_rate": 0.00010275543423681621,
+      "loss": 0.2333,
+      "step": 310
+    },
+    {
+      "epoch": 2.962962962962963,
+      "grad_norm": 0.71484375,
+      "learning_rate": 9.724456576318381e-05,
+      "loss": 0.2251,
+      "step": 320
+    },
+    {
+      "epoch": 3.0555555555555554,
+      "grad_norm": 0.46875,
+      "learning_rate": 9.174206545276677e-05,
+      "loss": 0.1187,
+      "step": 330
+    },
+    {
+      "epoch": 3.148148148148148,
+      "grad_norm": 0.423828125,
+      "learning_rate": 8.626464421815919e-05,
+      "loss": 0.0489,
+      "step": 340
+    },
+    {
+      "epoch": 3.240740740740741,
+      "grad_norm": 0.333984375,
+      "learning_rate": 8.082893680762619e-05,
+      "loss": 0.0581,
+      "step": 350
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 0.376953125,
+      "learning_rate": 7.54514512859201e-05,
+      "loss": 0.0472,
+      "step": 360
+    },
+    {
+      "epoch": 3.425925925925926,
+      "grad_norm": 0.408203125,
+      "learning_rate": 7.014851889983057e-05,
+      "loss": 0.0478,
+      "step": 370
+    },
+    {
+      "epoch": 3.5185185185185186,
+      "grad_norm": 0.4375,
+      "learning_rate": 6.493624448072457e-05,
+      "loss": 0.0588,
+      "step": 380
+    },
+    {
+      "epoch": 3.611111111111111,
+      "grad_norm": 0.3515625,
+      "learning_rate": 5.983045753470308e-05,
+      "loss": 0.0446,
+      "step": 390
+    },
+    {
+      "epoch": 3.7037037037037037,
+      "grad_norm": 0.357421875,
+      "learning_rate": 5.484666416891109e-05,
+      "loss": 0.0379,
+      "step": 400
+    },
+    {
+      "epoch": 3.7037037037037037,
+      "eval_loss": 2.7180562019348145,
+      "eval_runtime": 26.1711,
+      "eval_samples_per_second": 57.353,
+      "eval_steps_per_second": 7.183,
+      "step": 400
     }
   ],
   "logging_steps": 10,
@@ -182,7 +330,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2990695522435072e+17,
+  "total_flos": 2.5981391044870144e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null