Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4d22a2be8ab87b81f9e940690340f053a69a407f497e8ac235fce3a22186b30
+oid sha256:058783886b049967d4af9788b5d5d669f5778857820043d462330a96a832d2c0
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:761d91a02e82d716033664e9b2bcf168b607ddd87ba97ab7d247d20ab8a2abe2
+oid sha256:3d0e5eb204c821cc824b1530ffae1161ef15a7aac7af3e46a3836f44f6d9590f
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b9446e6179d1b677364f3d017edd1e4bf13f506d7d9f22ea86463529ec72bbf
+oid sha256:c2f1ed43d34077c0cbe6a0f88136e32289e8c5177833fdfd4e9b71dcac82f54e
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:072cd75b5e774f2273ed64aa239f1ab5f8696623be7e76e585a0b9e89a78f37d
+oid sha256:b534ab8e8517e0c6771c0517b7c6ca405d64b699a1ec4bf1386feab69ad4b0d5
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98348165f04d3fdba91aa7270bfc7b8d3b45ceba40522305ad8d1c5bc1b8daf4
+oid sha256:c1a9295e4c4a546113ec0ec98bd86153b2528f41880a63ef5b18dec809c3e017
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80c96fa49497674a71cc619c536290c7f1168c710d03fff81ba7c78482b2906d
+oid sha256:488c447eb2fc1166e3498312649a51a5f87298d695eb1271ea93d2011d80fb52
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99fc9c0ec571f76cf9b6d1229601c5173899cd18104e487c5627f5f4c56c6e8a
+oid sha256:46fa8207e86dee7d50b0ab12f1dd18c4426e8c65d06f97f8b2bd004a747e9cfa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.007770913470878502,
+  "epoch": 0.015541826941757004,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 987.178,
       "eval_steps_per_second": 123.431,
       "step": 25
+    },
+    {
+      "epoch": 0.008081750009713642,
+      "grad_norm": 0.12113793939352036,
+      "learning_rate": 7.68649804173412e-05,
+      "loss": 10.3664,
+      "step": 26
+    },
+    {
+      "epoch": 0.008392586548548782,
+      "grad_norm": 0.1222296953201294,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 10.358,
+      "step": 27
+    },
+    {
+      "epoch": 0.008703423087383921,
+      "grad_norm": 0.1611909419298172,
+      "learning_rate": 7.308743066175172e-05,
+      "loss": 10.3606,
+      "step": 28
+    },
+    {
+      "epoch": 0.009014259626219063,
+      "grad_norm": 0.16634967923164368,
+      "learning_rate": 7.113091308703498e-05,
+      "loss": 10.375,
+      "step": 29
+    },
+    {
+      "epoch": 0.009325096165054203,
+      "grad_norm": 0.20806021988391876,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 10.3651,
+      "step": 30
+    },
+    {
+      "epoch": 0.009635932703889342,
+      "grad_norm": 0.18134745955467224,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 10.3622,
+      "step": 31
+    },
+    {
+      "epoch": 0.009946769242724482,
+      "grad_norm": 0.23395313322544098,
+      "learning_rate": 6.503528997521366e-05,
+      "loss": 10.3641,
+      "step": 32
+    },
+    {
+      "epoch": 0.010257605781559622,
+      "grad_norm": 0.24909980595111847,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 10.3626,
+      "step": 33
+    },
+    {
+      "epoch": 0.010568442320394762,
+      "grad_norm": 0.2704538106918335,
+      "learning_rate": 6.0821980696905146e-05,
+      "loss": 10.3612,
+      "step": 34
+    },
+    {
+      "epoch": 0.010879278859229902,
+      "grad_norm": 0.30182722210884094,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 10.3618,
+      "step": 35
+    },
+    {
+      "epoch": 0.011190115398065043,
+      "grad_norm": 0.30596181750297546,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 10.3671,
+      "step": 36
+    },
+    {
+      "epoch": 0.011500951936900183,
+      "grad_norm": 0.3400585651397705,
+      "learning_rate": 5.435778713738292e-05,
+      "loss": 10.3525,
+      "step": 37
+    },
+    {
+      "epoch": 0.011811788475735323,
+      "grad_norm": 0.25906017422676086,
+      "learning_rate": 5.218096936826681e-05,
+      "loss": 10.3615,
+      "step": 38
+    },
+    {
+      "epoch": 0.012122625014570463,
+      "grad_norm": 0.16712762415409088,
+      "learning_rate": 5e-05,
+      "loss": 10.3603,
+      "step": 39
+    },
+    {
+      "epoch": 0.012433461553405602,
+      "grad_norm": 0.18277670443058014,
+      "learning_rate": 4.781903063173321e-05,
+      "loss": 10.3596,
+      "step": 40
+    },
+    {
+      "epoch": 0.012744298092240742,
+      "grad_norm": 0.21423067152500153,
+      "learning_rate": 4.564221286261709e-05,
+      "loss": 10.3575,
+      "step": 41
+    },
+    {
+      "epoch": 0.013055134631075884,
+      "grad_norm": 0.2574392855167389,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 10.3572,
+      "step": 42
+    },
+    {
+      "epoch": 0.013365971169911024,
+      "grad_norm": 0.29102233052253723,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 10.354,
+      "step": 43
+    },
+    {
+      "epoch": 0.013676807708746163,
+      "grad_norm": 0.30868732929229736,
+      "learning_rate": 3.917801930309486e-05,
+      "loss": 10.3597,
+      "step": 44
+    },
+    {
+      "epoch": 0.013987644247581303,
+      "grad_norm": 0.26494768261909485,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 10.3587,
+      "step": 45
+    },
+    {
+      "epoch": 0.014298480786416443,
+      "grad_norm": 0.31784704327583313,
+      "learning_rate": 3.4964710024786354e-05,
+      "loss": 10.3514,
+      "step": 46
+    },
+    {
+      "epoch": 0.014609317325251583,
+      "grad_norm": 0.31726884841918945,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 10.3488,
+      "step": 47
+    },
+    {
+      "epoch": 0.014920153864086723,
+      "grad_norm": 0.3178487718105316,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 10.3527,
+      "step": 48
+    },
+    {
+      "epoch": 0.015230990402921864,
+      "grad_norm": 0.42220181226730347,
+      "learning_rate": 2.886908691296504e-05,
+      "loss": 10.3521,
+      "step": 49
+    },
+    {
+      "epoch": 0.015541826941757004,
+      "grad_norm": 0.511695146560669,
+      "learning_rate": 2.6912569338248315e-05,
+      "loss": 10.3413,
+      "step": 50
+    },
+    {
+      "epoch": 0.015541826941757004,
+      "eval_loss": 10.35302734375,
+      "eval_runtime": 10.9637,
+      "eval_samples_per_second": 988.445,
+      "eval_steps_per_second": 123.59,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -217,7 +400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 10692014899200.0,
+  "total_flos": 21384029798400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null