Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b03a917a02754e9a77cf3e5e57c3a0dbf57b8fc6076c9b26a5729fc9d085c1b
+oid sha256:7a2fc12336adce739348a07a3a6d78256e08ed2f2ba0caa26c2e107c245655cb
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ed3e1ba4684e0654116d41e73363f4f607909df44cb228317f47e5c2a162930
+oid sha256:201dffbeafdcb3736d3f42bf8fc9643c657e36567ebd673ad90dfe9ffc9fd21c
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81c43d23039ca0db3b6179db8c8e7a1c9392174a68863d042805df95ddea9b38
+oid sha256:a10b30c9eb6fa58f462effd0387a91e467102f189329d79b95990979c2e03389
 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": 0.003987717829086414,
+  "epoch": 0.005981576743629621,
   "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": 0.2402,
       "step": 50
+    },
+    {
+      "epoch": 0.004067472185668142,
+      "grad_norm": 0.019093716517090797,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 0.0003,
+      "step": 51
+    },
+    {
+      "epoch": 0.00414722654224987,
+      "grad_norm": 6.016909122467041,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 0.1171,
+      "step": 52
+    },
+    {
+      "epoch": 0.0042269808988315985,
+      "grad_norm": 3.237635850906372,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 0.0479,
+      "step": 53
+    },
+    {
+      "epoch": 0.004306735255413327,
+      "grad_norm": 0.45389387011528015,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 0.0071,
+      "step": 54
+    },
+    {
+      "epoch": 0.004306735255413327,
+      "eval_loss": 0.039176907390356064,
+      "eval_runtime": 553.614,
+      "eval_samples_per_second": 19.073,
+      "eval_steps_per_second": 2.384,
+      "step": 54
+    },
+    {
+      "epoch": 0.004386489611995055,
+      "grad_norm": 1.7394068241119385,
+      "learning_rate": 5e-05,
+      "loss": 0.0313,
+      "step": 55
+    },
+    {
+      "epoch": 0.004466243968576784,
+      "grad_norm": 1.723865270614624,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 0.0238,
+      "step": 56
+    },
+    {
+      "epoch": 0.004545998325158512,
+      "grad_norm": 2.5933642387390137,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 0.0253,
+      "step": 57
+    },
+    {
+      "epoch": 0.00462575268174024,
+      "grad_norm": 0.04176973178982735,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.0006,
+      "step": 58
+    },
+    {
+      "epoch": 0.004705507038321968,
+      "grad_norm": 3.8093903064727783,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 0.0485,
+      "step": 59
+    },
+    {
+      "epoch": 0.004785261394903696,
+      "grad_norm": 4.592166900634766,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.0812,
+      "step": 60
+    },
+    {
+      "epoch": 0.0048650157514854245,
+      "grad_norm": 0.9173868298530579,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 0.0104,
+      "step": 61
+    },
+    {
+      "epoch": 0.0049447701080671536,
+      "grad_norm": 1.9208635091781616,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 0.0213,
+      "step": 62
+    },
+    {
+      "epoch": 0.005024524464648882,
+      "grad_norm": 2.4270222187042236,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 0.0342,
+      "step": 63
+    },
+    {
+      "epoch": 0.005024524464648882,
+      "eval_loss": 0.02897912636399269,
+      "eval_runtime": 553.584,
+      "eval_samples_per_second": 19.074,
+      "eval_steps_per_second": 2.384,
+      "step": 63
+    },
+    {
+      "epoch": 0.00510427882123061,
+      "grad_norm": 0.15133006870746613,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.0014,
+      "step": 64
+    },
+    {
+      "epoch": 0.005184033177812338,
+      "grad_norm": 3.995213747024536,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 0.2232,
+      "step": 65
+    },
+    {
+      "epoch": 0.005263787534394066,
+      "grad_norm": 0.10878176242113113,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.0011,
+      "step": 66
+    },
+    {
+      "epoch": 0.005343541890975794,
+      "grad_norm": 0.055173374712467194,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 0.0007,
+      "step": 67
+    },
+    {
+      "epoch": 0.005423296247557522,
+      "grad_norm": 5.00130558013916,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 0.1167,
+      "step": 68
+    },
+    {
+      "epoch": 0.005503050604139251,
+      "grad_norm": 0.32802918553352356,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 0.0026,
+      "step": 69
+    },
+    {
+      "epoch": 0.00558280496072098,
+      "grad_norm": 0.10490323603153229,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0014,
+      "step": 70
+    },
+    {
+      "epoch": 0.005662559317302708,
+      "grad_norm": 0.014080111868679523,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 0.0002,
+      "step": 71
+    },
+    {
+      "epoch": 0.005742313673884436,
+      "grad_norm": 0.021097006276249886,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 0.0005,
+      "step": 72
+    },
+    {
+      "epoch": 0.005742313673884436,
+      "eval_loss": 0.038278449326753616,
+      "eval_runtime": 553.4245,
+      "eval_samples_per_second": 19.079,
+      "eval_steps_per_second": 2.385,
+      "step": 72
+    },
+    {
+      "epoch": 0.005822068030466164,
+      "grad_norm": 0.014087294228374958,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.0002,
+      "step": 73
+    },
+    {
+      "epoch": 0.005901822387047892,
+      "grad_norm": 0.00338623090647161,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 0.0001,
+      "step": 74
+    },
+    {
+      "epoch": 0.005981576743629621,
+      "grad_norm": 0.0011795306345447898,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.0,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.746530781980262e+16,
+  "total_flos": 5.601248990881382e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null