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:f348b509c1eebfe9f36f6a02c0c6222caa1fb3130acfaab5e1e3ed000af21a2d
+oid sha256:de2459e18535c913b117b3b8cf26fd63b4f917517519775fc7aa974504fa53df
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8a45b6d17c1c86bb1620152c898c77f374a7fb59ddd8d9968f7e79538b0f29b
+oid sha256:c4a289c5be8d3cb6435d637db48e6c277117a778fac7178b89bdcccec0e773ac
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c08c9f2db3519491f65c896dc5570f0688363fea4110372251c117212111fc45
+oid sha256:2ee9440c38b11df1bad9c246eb1b0880c612c59b45e12b698debf583c3696051
 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": 0.14749262536873156,
+  "epoch": 0.22123893805309736,
   "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": 2.5142,
       "step": 50
+    },
+    {
+      "epoch": 0.1504424778761062,
+      "grad_norm": 1.5647395849227905,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 2.0823,
+      "step": 51
+    },
+    {
+      "epoch": 0.15339233038348082,
+      "grad_norm": 3.6214590072631836,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 2.4263,
+      "step": 52
+    },
+    {
+      "epoch": 0.15634218289085547,
+      "grad_norm": 2.2273218631744385,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 1.8634,
+      "step": 53
+    },
+    {
+      "epoch": 0.1592920353982301,
+      "grad_norm": 2.075181722640991,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 2.1057,
+      "step": 54
+    },
+    {
+      "epoch": 0.1592920353982301,
+      "eval_loss": 0.9436812996864319,
+      "eval_runtime": 44.4269,
+      "eval_samples_per_second": 6.438,
+      "eval_steps_per_second": 0.81,
+      "step": 54
+    },
+    {
+      "epoch": 0.16224188790560473,
+      "grad_norm": 2.0070507526397705,
+      "learning_rate": 5e-05,
+      "loss": 1.7728,
+      "step": 55
+    },
+    {
+      "epoch": 0.16519174041297935,
+      "grad_norm": 2.2338101863861084,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 2.7216,
+      "step": 56
+    },
+    {
+      "epoch": 0.168141592920354,
+      "grad_norm": 2.3538854122161865,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 1.6894,
+      "step": 57
+    },
+    {
+      "epoch": 0.1710914454277286,
+      "grad_norm": 2.551027536392212,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 1.4082,
+      "step": 58
+    },
+    {
+      "epoch": 0.17404129793510326,
+      "grad_norm": 2.7152366638183594,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 1.7138,
+      "step": 59
+    },
+    {
+      "epoch": 0.17699115044247787,
+      "grad_norm": 3.2682361602783203,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 2.0795,
+      "step": 60
+    },
+    {
+      "epoch": 0.17994100294985252,
+      "grad_norm": 1.910207748413086,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 2.4073,
+      "step": 61
+    },
+    {
+      "epoch": 0.18289085545722714,
+      "grad_norm": 2.7701568603515625,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 1.678,
+      "step": 62
+    },
+    {
+      "epoch": 0.18584070796460178,
+      "grad_norm": 2.447645425796509,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 1.9186,
+      "step": 63
+    },
+    {
+      "epoch": 0.18584070796460178,
+      "eval_loss": 0.9331210255622864,
+      "eval_runtime": 44.3944,
+      "eval_samples_per_second": 6.442,
+      "eval_steps_per_second": 0.811,
+      "step": 63
+    },
+    {
+      "epoch": 0.1887905604719764,
+      "grad_norm": 2.811461925506592,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 2.0873,
+      "step": 64
+    },
+    {
+      "epoch": 0.19174041297935104,
+      "grad_norm": 2.722278594970703,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 1.8269,
+      "step": 65
+    },
+    {
+      "epoch": 0.19469026548672566,
+      "grad_norm": 2.2737720012664795,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 1.8935,
+      "step": 66
+    },
+    {
+      "epoch": 0.1976401179941003,
+      "grad_norm": 1.9448575973510742,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 1.4455,
+      "step": 67
+    },
+    {
+      "epoch": 0.20058997050147492,
+      "grad_norm": 2.384688138961792,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 1.9643,
+      "step": 68
+    },
+    {
+      "epoch": 0.20353982300884957,
+      "grad_norm": 2.049166440963745,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 2.3775,
+      "step": 69
+    },
+    {
+      "epoch": 0.20648967551622419,
+      "grad_norm": 2.747662305831909,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.7945,
+      "step": 70
+    },
+    {
+      "epoch": 0.20943952802359883,
+      "grad_norm": 2.058532953262329,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 1.4522,
+      "step": 71
+    },
+    {
+      "epoch": 0.21238938053097345,
+      "grad_norm": 2.542921543121338,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 2.0277,
+      "step": 72
+    },
+    {
+      "epoch": 0.21238938053097345,
+      "eval_loss": 0.9295855760574341,
+      "eval_runtime": 44.4249,
+      "eval_samples_per_second": 6.438,
+      "eval_steps_per_second": 0.81,
+      "step": 72
+    },
+    {
+      "epoch": 0.2153392330383481,
+      "grad_norm": 2.58382248878479,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 1.7377,
+      "step": 73
+    },
+    {
+      "epoch": 0.2182890855457227,
+      "grad_norm": 2.8606531620025635,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 1.8194,
+      "step": 74
+    },
+    {
+      "epoch": 0.22123893805309736,
+      "grad_norm": 3.316101551055908,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 2.3525,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.347789697024e+16,
+  "total_flos": 9.521684545536e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null