Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:279f8d27e63b270a28934ba0b989281636b908b427e466bae77f83111be67ead
+oid sha256:3b72d5dfb4a7fc33029d67f39e553d5609bdc83b7ab5cce6bbef8d0ac70abbeb
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d67da7f92ef05a0bfe8287c45d88e657140f5ec3de5472d2748f8d1c182e261
+oid sha256:406a29e9e5d8cbcf4c4f8407db452bfd73a11d12ce71dde2893f722055042bf5
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:053c8e851ce140de0bd5ca1a996eb4fec1cc7160c01247329721140fdf1ba1f9
+oid sha256:c96e3fdc37adc43f609f641e42fab9fde276ad55fd08962ced6780dfb7ea43e6
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d49f6e75049f74209066023d6f98219ce5a745c3e0373c2b72cd2cd2077c72c
+oid sha256:fb05c611a3805157dc2d136f20f093e8b4986be1ee53b08311ddcbc2f55da26a
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf5cd5b565a32377639fd2c244098a59240f1844e4078e4e7d30af5b5eb3bf14
+oid sha256:80c90b7266a2dd40f68163aafdfed9c3b834bf78ad9021f0aea142729ebb3a9c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56e15726c42ce6197c9243c0a13ef9a114bc2190e73c1abe3d8fbebcca8d3e1c
+oid sha256:2cd3051469accba81f5a37ad56e2e49c81902a16b97b19e7801e673c080bdf15
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8547008547008547,
+  "epoch": 1.7094017094017095,
   "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": 14.274,
       "eval_steps_per_second": 3.711,
       "step": 25
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.28909528255462646,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.9418,
+      "step": 26
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "grad_norm": 0.38391032814979553,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.0341,
+      "step": 27
+    },
+    {
+      "epoch": 0.9572649572649573,
+      "grad_norm": 0.44489622116088867,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.9819,
+      "step": 28
+    },
+    {
+      "epoch": 0.9914529914529915,
+      "grad_norm": 0.6754913330078125,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.9653,
+      "step": 29
+    },
+    {
+      "epoch": 1.0256410256410255,
+      "grad_norm": 0.5481194853782654,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.4565,
+      "step": 30
+    },
+    {
+      "epoch": 1.0598290598290598,
+      "grad_norm": 0.2325354814529419,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.7719,
+      "step": 31
+    },
+    {
+      "epoch": 1.0940170940170941,
+      "grad_norm": 0.26181185245513916,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.8039,
+      "step": 32
+    },
+    {
+      "epoch": 1.1282051282051282,
+      "grad_norm": 0.2746793329715729,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.8383,
+      "step": 33
+    },
+    {
+      "epoch": 1.1623931623931625,
+      "grad_norm": 0.28374120593070984,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.905,
+      "step": 34
+    },
+    {
+      "epoch": 1.1965811965811965,
+      "grad_norm": 0.4092039167881012,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.0047,
+      "step": 35
+    },
+    {
+      "epoch": 1.2307692307692308,
+      "grad_norm": 0.5275164246559143,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.8573,
+      "step": 36
+    },
+    {
+      "epoch": 1.264957264957265,
+      "grad_norm": 0.2732887864112854,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.664,
+      "step": 37
+    },
+    {
+      "epoch": 1.2991452991452992,
+      "grad_norm": 0.23111304640769958,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.7862,
+      "step": 38
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.2312902808189392,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.7616,
+      "step": 39
+    },
+    {
+      "epoch": 1.3675213675213675,
+      "grad_norm": 0.25998955965042114,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.837,
+      "step": 40
+    },
+    {
+      "epoch": 1.4017094017094016,
+      "grad_norm": 0.3226254880428314,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.9217,
+      "step": 41
+    },
+    {
+      "epoch": 1.435897435897436,
+      "grad_norm": 0.476153165102005,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.006,
+      "step": 42
+    },
+    {
+      "epoch": 1.4700854700854702,
+      "grad_norm": 0.47047027945518494,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.7943,
+      "step": 43
+    },
+    {
+      "epoch": 1.5042735042735043,
+      "grad_norm": 0.2968030571937561,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.5807,
+      "step": 44
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "grad_norm": 0.2597537934780121,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.8635,
+      "step": 45
+    },
+    {
+      "epoch": 1.5726495726495726,
+      "grad_norm": 0.2324274331331253,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.7664,
+      "step": 46
+    },
+    {
+      "epoch": 1.606837606837607,
+      "grad_norm": 0.249767005443573,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.7848,
+      "step": 47
+    },
+    {
+      "epoch": 1.641025641025641,
+      "grad_norm": 0.29912737011909485,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.8973,
+      "step": 48
+    },
+    {
+      "epoch": 1.6752136752136753,
+      "grad_norm": 0.40372592210769653,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.9817,
+      "step": 49
+    },
+    {
+      "epoch": 1.7094017094017095,
+      "grad_norm": 0.47870293259620667,
+      "learning_rate": 1e-05,
+      "loss": 0.8148,
+      "step": 50
+    },
+    {
+      "epoch": 1.7094017094017095,
+      "eval_loss": 0.8940553069114685,
+      "eval_runtime": 3.5034,
+      "eval_samples_per_second": 14.272,
+      "eval_steps_per_second": 3.711,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -212,12 +395,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null