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:c7bbab457f4ce71dda9f00f32cf89ac4ca71dd07a0f14d7e92cef79246c5d58b
+oid sha256:d45fe14428523c371a6bbe4899c6007627ee0f27cf32451bf7809e00accdb265
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3804e2c1b2ba737fb4264dc18ff2334e44a440b781703a90aa7740d6b1fd5e12
+oid sha256:fc62b813d7d312b3876f460accee483d67d79e8efe14db60d82fbe315e8133be
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e911014c177207add8d175713b58ac2b2f82279c0020814d4d56ddcb21a16484
+oid sha256:38416d88c9d2d10168ce8eb5c0e25ba2e76e46134432cb12986cab3aa7f61db4
 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": 0.0082904990880451,
+  "epoch": 0.01243574863206765,
   "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": 0.5151,
       "step": 50
+    },
+    {
+      "epoch": 0.008456309069806002,
+      "grad_norm": 2.6409878730773926,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 0.5612,
+      "step": 51
+    },
+    {
+      "epoch": 0.008622119051566905,
+      "grad_norm": 3.065234422683716,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 0.8439,
+      "step": 52
+    },
+    {
+      "epoch": 0.008787929033327806,
+      "grad_norm": 3.303943395614624,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 0.9554,
+      "step": 53
+    },
+    {
+      "epoch": 0.008953739015088709,
+      "grad_norm": 1.6492938995361328,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 0.5354,
+      "step": 54
+    },
+    {
+      "epoch": 0.008953739015088709,
+      "eval_loss": 0.340312123298645,
+      "eval_runtime": 1576.0534,
+      "eval_samples_per_second": 3.223,
+      "eval_steps_per_second": 0.403,
+      "step": 54
+    },
+    {
+      "epoch": 0.00911954899684961,
+      "grad_norm": 3.8954522609710693,
+      "learning_rate": 5e-05,
+      "loss": 1.0515,
+      "step": 55
+    },
+    {
+      "epoch": 0.009285358978610513,
+      "grad_norm": 3.292879343032837,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 0.8962,
+      "step": 56
+    },
+    {
+      "epoch": 0.009451168960371414,
+      "grad_norm": 2.53454327583313,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 0.4575,
+      "step": 57
+    },
+    {
+      "epoch": 0.009616978942132317,
+      "grad_norm": 1.6766483783721924,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.4632,
+      "step": 58
+    },
+    {
+      "epoch": 0.009782788923893218,
+      "grad_norm": 1.7836233377456665,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 0.4928,
+      "step": 59
+    },
+    {
+      "epoch": 0.00994859890565412,
+      "grad_norm": 2.2400903701782227,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.6358,
+      "step": 60
+    },
+    {
+      "epoch": 0.010114408887415022,
+      "grad_norm": 1.9944827556610107,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 0.5992,
+      "step": 61
+    },
+    {
+      "epoch": 0.010280218869175925,
+      "grad_norm": 2.788837194442749,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 0.5151,
+      "step": 62
+    },
+    {
+      "epoch": 0.010446028850936826,
+      "grad_norm": 1.742371916770935,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 0.4412,
+      "step": 63
+    },
+    {
+      "epoch": 0.010446028850936826,
+      "eval_loss": 0.2952826917171478,
+      "eval_runtime": 1575.7706,
+      "eval_samples_per_second": 3.223,
+      "eval_steps_per_second": 0.403,
+      "step": 63
+    },
+    {
+      "epoch": 0.010611838832697729,
+      "grad_norm": 2.136950969696045,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.4605,
+      "step": 64
+    },
+    {
+      "epoch": 0.01077764881445863,
+      "grad_norm": 2.725506067276001,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 0.626,
+      "step": 65
+    },
+    {
+      "epoch": 0.010943458796219533,
+      "grad_norm": 1.9136492013931274,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.5691,
+      "step": 66
+    },
+    {
+      "epoch": 0.011109268777980434,
+      "grad_norm": 2.0167644023895264,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 0.481,
+      "step": 67
+    },
+    {
+      "epoch": 0.011275078759741337,
+      "grad_norm": 2.068988561630249,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 0.5006,
+      "step": 68
+    },
+    {
+      "epoch": 0.011440888741502238,
+      "grad_norm": 1.7421566247940063,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 0.4953,
+      "step": 69
+    },
+    {
+      "epoch": 0.01160669872326314,
+      "grad_norm": 1.764000415802002,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.4209,
+      "step": 70
+    },
+    {
+      "epoch": 0.011772508705024042,
+      "grad_norm": 1.9363012313842773,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 0.37,
+      "step": 71
+    },
+    {
+      "epoch": 0.011938318686784945,
+      "grad_norm": 3.3709402084350586,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 0.5696,
+      "step": 72
+    },
+    {
+      "epoch": 0.011938318686784945,
+      "eval_loss": 0.30603596568107605,
+      "eval_runtime": 1575.9112,
+      "eval_samples_per_second": 3.223,
+      "eval_steps_per_second": 0.403,
+      "step": 72
+    },
+    {
+      "epoch": 0.012104128668545846,
+      "grad_norm": 4.627692699432373,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.9927,
+      "step": 73
+    },
+    {
+      "epoch": 0.012269938650306749,
+      "grad_norm": 3.018941640853882,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 0.643,
+      "step": 74
+    },
+    {
+      "epoch": 0.01243574863206765,
+      "grad_norm": 2.8828186988830566,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.6989,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2695579394048e+17,
+  "total_flos": 1.9043369091072e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null