Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c331626b184f08fed5487535192256ea96faad90adefe4e1ad46eb3f553696d
+oid sha256:0c80954338859951571ce2266d837c1e20e2c911ea77eda513af6cf84da24478
 size 13587864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fb06be01e5059ac8d0974d478720be53ed4482478b2f64e5094b6b15e6c0831
+oid sha256:3b2c2f5fde31ceb864f4b134d23daf5d802d182c3da9b7ead96652398e60e6e2
 size 27273018

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17e1f0fd2d004d6caaae844aa17b92356b2e2f60ef5bfaf5353e49ccd0051ffa
+oid sha256:2c88366e4cedd829c09c5fe7059b8e2e98aca6c5ecd80e83fa5290e51d4813d6
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:981bbea8034bbbae85baf44fc3a7f5bd1463eae4931e71f483cdca42e7a37e82
+oid sha256:e37fdc46c9ceacc4f09fb079980eedde483f3261a807a717ac38bb84282cfbc0
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1793234b26d0e6ac7ecfc78a9a7d47b949a0319dc3c10c322d5f7a878592c6c9
+oid sha256:7531acfa0ec9fa2b40b0cd20bab3f5a106f4cba2bace97e330dcfa83316c6148
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce143f3192cb1b2e626d251c64dac68350718e07c33521f586159568d189c078
+oid sha256:3c9f53c748ab56977e5d0b2dabfb603fcb816a36a8711e81b4f65d5a8fb7d27c
 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": 0.02852253280091272,
+  "epoch": 0.04278379920136908,
   "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": 2.3786,
       "step": 50
+    },
+    {
+      "epoch": 0.029092983456930975,
+      "grad_norm": 0.6005697250366211,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 2.4816,
+      "step": 51
+    },
+    {
+      "epoch": 0.02966343411294923,
+      "grad_norm": 0.7842492461204529,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 2.3731,
+      "step": 52
+    },
+    {
+      "epoch": 0.030233884768967486,
+      "grad_norm": 0.6030087471008301,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 2.3131,
+      "step": 53
+    },
+    {
+      "epoch": 0.03080433542498574,
+      "grad_norm": 0.6377494931221008,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 2.3366,
+      "step": 54
+    },
+    {
+      "epoch": 0.03080433542498574,
+      "eval_loss": 2.388643503189087,
+      "eval_runtime": 8.0803,
+      "eval_samples_per_second": 730.666,
+      "eval_steps_per_second": 22.895,
+      "step": 54
+    },
+    {
+      "epoch": 0.03137478608100399,
+      "grad_norm": 0.7002130746841431,
+      "learning_rate": 5e-05,
+      "loss": 2.2085,
+      "step": 55
+    },
+    {
+      "epoch": 0.03194523673702225,
+      "grad_norm": 0.7296257615089417,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 2.3402,
+      "step": 56
+    },
+    {
+      "epoch": 0.032515687393040504,
+      "grad_norm": 0.6167798638343811,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 2.315,
+      "step": 57
+    },
+    {
+      "epoch": 0.03308613804905876,
+      "grad_norm": 0.6555004119873047,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 2.4566,
+      "step": 58
+    },
+    {
+      "epoch": 0.03365658870507701,
+      "grad_norm": 0.6642969846725464,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 2.3569,
+      "step": 59
+    },
+    {
+      "epoch": 0.034227039361095266,
+      "grad_norm": 0.736000657081604,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 2.2542,
+      "step": 60
+    },
+    {
+      "epoch": 0.03479749001711352,
+      "grad_norm": 0.6817083358764648,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 2.4191,
+      "step": 61
+    },
+    {
+      "epoch": 0.03536794067313177,
+      "grad_norm": 0.6803595423698425,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 2.3597,
+      "step": 62
+    },
+    {
+      "epoch": 0.03593839132915003,
+      "grad_norm": 0.724940299987793,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 2.2966,
+      "step": 63
+    },
+    {
+      "epoch": 0.03593839132915003,
+      "eval_loss": 2.291182518005371,
+      "eval_runtime": 8.0432,
+      "eval_samples_per_second": 734.038,
+      "eval_steps_per_second": 23.001,
+      "step": 63
+    },
+    {
+      "epoch": 0.03650884198516828,
+      "grad_norm": 0.6571291089057922,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 2.1965,
+      "step": 64
+    },
+    {
+      "epoch": 0.037079292641186534,
+      "grad_norm": 0.6792440414428711,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 2.2352,
+      "step": 65
+    },
+    {
+      "epoch": 0.037649743297204795,
+      "grad_norm": 0.6271291971206665,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 2.262,
+      "step": 66
+    },
+    {
+      "epoch": 0.03822019395322305,
+      "grad_norm": 0.6394158005714417,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 2.3448,
+      "step": 67
+    },
+    {
+      "epoch": 0.0387906446092413,
+      "grad_norm": 0.6799787878990173,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 2.1793,
+      "step": 68
+    },
+    {
+      "epoch": 0.039361095265259556,
+      "grad_norm": 0.6452582478523254,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 2.2576,
+      "step": 69
+    },
+    {
+      "epoch": 0.03993154592127781,
+      "grad_norm": 0.6168031692504883,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.1982,
+      "step": 70
+    },
+    {
+      "epoch": 0.040501996577296064,
+      "grad_norm": 0.6837731003761292,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 2.1536,
+      "step": 71
+    },
+    {
+      "epoch": 0.04107244723331432,
+      "grad_norm": 0.7503871917724609,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 2.2486,
+      "step": 72
+    },
+    {
+      "epoch": 0.04107244723331432,
+      "eval_loss": 2.22768497467041,
+      "eval_runtime": 8.0532,
+      "eval_samples_per_second": 733.125,
+      "eval_steps_per_second": 22.972,
+      "step": 72
+    },
+    {
+      "epoch": 0.04164289788933257,
+      "grad_norm": 0.6214445233345032,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 2.3014,
+      "step": 73
+    },
+    {
+      "epoch": 0.042213348545350825,
+      "grad_norm": 0.5839588046073914,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 2.1236,
+      "step": 74
+    },
+    {
+      "epoch": 0.04278379920136908,
+      "grad_norm": 0.6537484526634216,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 2.0327,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2783693600980992.0,
+  "total_flos": 4172069461819392.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null