Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f059777c7257a9b8551361bb6a8463778375a07cd0b88f16fc506af5661c926
+oid sha256:d59c541daad881a2bcf7c3fa2df078c9fee46add5727a0a9d5b906b61ff6de3b
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4121eecb0f08728587aa525f333d63ed355d8e3750edaedf676e26401be02f1c
+oid sha256:ff2267d7748a41531488b101470ffa97098788692fcf734acfe416020f1c2ccc
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb9517b7ce59c47365939baf2f50e6bfd58d4414b9c61ed194de990178b59d75
+oid sha256:9418a68e5819dc4b84034984f04774a6cc7da23a601f4d1f77e1c7bf288f18ec
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a89ffc445067fef9d6d02bb3ff9e61d5e3209e6fa67c7259b3b364b90dbaa2cd
+oid sha256:f23e2214bcafb439ebc7528dcc283ef6218d509a276c0baff0743503ecbe3d92
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0010590639992374739,
+  "epoch": 0.0015885959988562108,
   "eval_steps": 9,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -405,6 +405,205 @@
       "learning_rate": 5.868240888334653e-05,
       "loss": 10.3602,
       "step": 50
+    },
+    {
+      "epoch": 0.0010802452792222233,
+      "grad_norm": 0.2696683704853058,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 10.3797,
+      "step": 51
+    },
+    {
+      "epoch": 0.0011014265592069728,
+      "grad_norm": 0.2767253518104553,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 10.3767,
+      "step": 52
+    },
+    {
+      "epoch": 0.0011226078391917223,
+      "grad_norm": 0.28129932284355164,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 10.3607,
+      "step": 53
+    },
+    {
+      "epoch": 0.0011437891191764717,
+      "grad_norm": 0.2902565598487854,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 10.3621,
+      "step": 54
+    },
+    {
+      "epoch": 0.0011437891191764717,
+      "eval_loss": 10.363870620727539,
+      "eval_runtime": 263.6718,
+      "eval_samples_per_second": 150.786,
+      "eval_steps_per_second": 18.849,
+      "step": 54
+    },
+    {
+      "epoch": 0.0011649703991612214,
+      "grad_norm": 0.25226110219955444,
+      "learning_rate": 5e-05,
+      "loss": 10.3868,
+      "step": 55
+    },
+    {
+      "epoch": 0.0011861516791459709,
+      "grad_norm": 0.3142261505126953,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 10.35,
+      "step": 56
+    },
+    {
+      "epoch": 0.0012073329591307204,
+      "grad_norm": 0.366685152053833,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 10.3823,
+      "step": 57
+    },
+    {
+      "epoch": 0.0012285142391154698,
+      "grad_norm": 0.2839343547821045,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 10.357,
+      "step": 58
+    },
+    {
+      "epoch": 0.0012496955191002193,
+      "grad_norm": 0.2913300395011902,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 10.3403,
+      "step": 59
+    },
+    {
+      "epoch": 0.0012708767990849688,
+      "grad_norm": 0.28911805152893066,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 10.351,
+      "step": 60
+    },
+    {
+      "epoch": 0.0012920580790697182,
+      "grad_norm": 0.33699050545692444,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 10.3366,
+      "step": 61
+    },
+    {
+      "epoch": 0.0013132393590544677,
+      "grad_norm": 0.2737447917461395,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 10.3459,
+      "step": 62
+    },
+    {
+      "epoch": 0.0013344206390392172,
+      "grad_norm": 0.26118916273117065,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 10.3575,
+      "step": 63
+    },
+    {
+      "epoch": 0.0013344206390392172,
+      "eval_loss": 10.358147621154785,
+      "eval_runtime": 264.4036,
+      "eval_samples_per_second": 150.369,
+      "eval_steps_per_second": 18.797,
+      "step": 63
+    },
+    {
+      "epoch": 0.0013556019190239666,
+      "grad_norm": 0.2942837178707123,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 10.3614,
+      "step": 64
+    },
+    {
+      "epoch": 0.001376783199008716,
+      "grad_norm": 0.34198886156082153,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 10.3492,
+      "step": 65
+    },
+    {
+      "epoch": 0.0013979644789934656,
+      "grad_norm": 0.30794763565063477,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 10.3687,
+      "step": 66
+    },
+    {
+      "epoch": 0.001419145758978215,
+      "grad_norm": 0.3069867491722107,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 10.3396,
+      "step": 67
+    },
+    {
+      "epoch": 0.0014403270389629645,
+      "grad_norm": 0.2907857298851013,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 10.3519,
+      "step": 68
+    },
+    {
+      "epoch": 0.001461508318947714,
+      "grad_norm": 0.2831253707408905,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 10.3592,
+      "step": 69
+    },
+    {
+      "epoch": 0.0014826895989324634,
+      "grad_norm": 0.2868959605693817,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 10.3545,
+      "step": 70
+    },
+    {
+      "epoch": 0.001503870878917213,
+      "grad_norm": 0.28792205452919006,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 10.3609,
+      "step": 71
+    },
+    {
+      "epoch": 0.0015250521589019624,
+      "grad_norm": 0.3293297588825226,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 10.3534,
+      "step": 72
+    },
+    {
+      "epoch": 0.0015250521589019624,
+      "eval_loss": 10.353981018066406,
+      "eval_runtime": 264.3866,
+      "eval_samples_per_second": 150.378,
+      "eval_steps_per_second": 18.798,
+      "step": 72
+    },
+    {
+      "epoch": 0.0015462334388867119,
+      "grad_norm": 0.3583596646785736,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 10.3684,
+      "step": 73
+    },
+    {
+      "epoch": 0.0015674147188714613,
+      "grad_norm": 0.33219587802886963,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 10.3615,
+      "step": 74
+    },
+    {
+      "epoch": 0.0015885959988562108,
+      "grad_norm": 0.3535849153995514,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 10.3904,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2615122329600.0,
+  "total_flos": 3922683494400.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null