Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4179ef2296562e52cce9db137c9b2c7fe45e23371b4eab3b1d940f8236f41a9e
+oid sha256:01e8da19d76c382a06fe3bc055f8406ba65f38cbb260ec6b25f5e99be62579e7
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ee61926f886a738682978343fecbd9486d35ab24377301ffa8ea46a06868a10
+oid sha256:9ccf27f75fb2a3c8bbac22620f026b824a5524e1ac0c0f2584475e9ef6663413
 size 118090

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68d8240f8b64502e023794a3da2d8c6aa526ac0f753e37b389fdd87097fabd55
+oid sha256:e0c7f44ec6860003f13de57bd2ad679abc76372e696f0ba64dcb096ad8c2d194
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f117663bca47e6dbbfa0c77eb3eb3ed1ed85a3dd0c9f866227e737a73eb5c422
+oid sha256:bd6efc3cf2283ba2318df09b4fccd81fc2c7c92f336f9b8fbed31252acffe51a
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a7d87a0b1f18c774b632725605bde69fd2b07215dcf9ac48e19e6caa47a6c61
+oid sha256:8ec5a5fa365a025d7b72e73ba5ae61435c717d5192c0a548efd67efffa7d01f8
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3daeca24213bd8e7f686bd89b9bb6ba8b6995471fd68b15febf485beb753100
+oid sha256:4ef8374d5b4a7b565c654f01afc3676c24946d4955ee4d27506c6d5576f109d2
 size 15024

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": 0.0217296827466319,
+  "epoch": 0.03259452411994785,
   "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": 10.2627,
       "step": 50
+    },
+    {
+      "epoch": 0.02216427640156454,
+      "grad_norm": 1.6855006217956543,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 10.2587,
+      "step": 51
+    },
+    {
+      "epoch": 0.022598870056497175,
+      "grad_norm": 1.6962989568710327,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 10.2377,
+      "step": 52
+    },
+    {
+      "epoch": 0.02303346371142981,
+      "grad_norm": 1.6561306715011597,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 10.2395,
+      "step": 53
+    },
+    {
+      "epoch": 0.02346805736636245,
+      "grad_norm": 1.6776403188705444,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 10.2517,
+      "step": 54
+    },
+    {
+      "epoch": 0.02346805736636245,
+      "eval_loss": 10.234784126281738,
+      "eval_runtime": 4.3928,
+      "eval_samples_per_second": 1764.474,
+      "eval_steps_per_second": 55.318,
+      "step": 54
+    },
+    {
+      "epoch": 0.023902651021295088,
+      "grad_norm": 1.6507542133331299,
+      "learning_rate": 5e-05,
+      "loss": 10.2472,
+      "step": 55
+    },
+    {
+      "epoch": 0.024337244676227728,
+      "grad_norm": 1.6575618982315063,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 10.2308,
+      "step": 56
+    },
+    {
+      "epoch": 0.024771838331160364,
+      "grad_norm": 1.6367050409317017,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 10.2184,
+      "step": 57
+    },
+    {
+      "epoch": 0.025206431986093004,
+      "grad_norm": 1.634709358215332,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 10.2335,
+      "step": 58
+    },
+    {
+      "epoch": 0.02564102564102564,
+      "grad_norm": 1.6403002738952637,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 10.2438,
+      "step": 59
+    },
+    {
+      "epoch": 0.02607561929595828,
+      "grad_norm": 1.5752891302108765,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 10.2285,
+      "step": 60
+    },
+    {
+      "epoch": 0.026510212950890916,
+      "grad_norm": 1.5749379396438599,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 10.2177,
+      "step": 61
+    },
+    {
+      "epoch": 0.026944806605823556,
+      "grad_norm": 1.5850154161453247,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 10.2273,
+      "step": 62
+    },
+    {
+      "epoch": 0.027379400260756193,
+      "grad_norm": 1.5233105421066284,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 10.2221,
+      "step": 63
+    },
+    {
+      "epoch": 0.027379400260756193,
+      "eval_loss": 10.216018676757812,
+      "eval_runtime": 4.396,
+      "eval_samples_per_second": 1763.203,
+      "eval_steps_per_second": 55.278,
+      "step": 63
+    },
+    {
+      "epoch": 0.027813993915688832,
+      "grad_norm": 1.5639811754226685,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 10.2026,
+      "step": 64
+    },
+    {
+      "epoch": 0.02824858757062147,
+      "grad_norm": 1.541033148765564,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 10.215,
+      "step": 65
+    },
+    {
+      "epoch": 0.028683181225554105,
+      "grad_norm": 1.4939786195755005,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 10.1985,
+      "step": 66
+    },
+    {
+      "epoch": 0.029117774880486745,
+      "grad_norm": 1.4225854873657227,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 10.2112,
+      "step": 67
+    },
+    {
+      "epoch": 0.02955236853541938,
+      "grad_norm": 1.5087547302246094,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 10.214,
+      "step": 68
+    },
+    {
+      "epoch": 0.02998696219035202,
+      "grad_norm": 1.4858537912368774,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 10.2253,
+      "step": 69
+    },
+    {
+      "epoch": 0.030421555845284658,
+      "grad_norm": 1.4683682918548584,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 10.2205,
+      "step": 70
+    },
+    {
+      "epoch": 0.030856149500217298,
+      "grad_norm": 1.4585028886795044,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 10.2128,
+      "step": 71
+    },
+    {
+      "epoch": 0.03129074315514994,
+      "grad_norm": 1.476791262626648,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 10.2148,
+      "step": 72
+    },
+    {
+      "epoch": 0.03129074315514994,
+      "eval_loss": 10.20433521270752,
+      "eval_runtime": 4.3833,
+      "eval_samples_per_second": 1768.31,
+      "eval_steps_per_second": 55.438,
+      "step": 72
+    },
+    {
+      "epoch": 0.03172533681008257,
+      "grad_norm": 1.4202309846878052,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 10.2038,
+      "step": 73
+    },
+    {
+      "epoch": 0.03215993046501521,
+      "grad_norm": 1.4229024648666382,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 10.1987,
+      "step": 74
+    },
+    {
+      "epoch": 0.03259452411994785,
+      "grad_norm": 1.4023692607879639,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 10.21,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 10460489318400.0,
+  "total_flos": 15690733977600.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null