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:f7730681e2b4047ab2e932bab443e584d478ba9e88ba17f3fb4637167b785394
+oid sha256:7d1ab521862ead76ebb9df07437ff66ef9cd30a4cac01e587f8eb20c99795ae6
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84ab9939bc69e88d91aa210f169813f6cf958fc07767ae321a8943810079a868
+oid sha256:b5d69c16d9fc9d7386cf0bebc0ccc9d2ac684edd9db4cc28ca24c0a9a6cc75d0
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:828a7e6e11ce6fb1a2356180954a5b20df0e28e99bfb6b79a96217eb20a3be28
+oid sha256:aeda752780d4d1e2c8cc72596036685baf31024a594da9ff5aea8a1a54a0f80c
 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": 0.002221629787612192,
+  "epoch": 0.0033324446814182885,
   "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": 1.1829,
       "step": 50
+    },
+    {
+      "epoch": 0.0022660623833644362,
+      "grad_norm": 3.211519479751587,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 0.9899,
+      "step": 51
+    },
+    {
+      "epoch": 0.00231049497911668,
+      "grad_norm": 2.8170390129089355,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 0.7881,
+      "step": 52
+    },
+    {
+      "epoch": 0.002354927574868924,
+      "grad_norm": 2.29962420463562,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 0.7825,
+      "step": 53
+    },
+    {
+      "epoch": 0.0023993601706211675,
+      "grad_norm": 3.250339984893799,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 0.8462,
+      "step": 54
+    },
+    {
+      "epoch": 0.0023993601706211675,
+      "eval_loss": 0.8770561814308167,
+      "eval_runtime": 2090.379,
+      "eval_samples_per_second": 9.067,
+      "eval_steps_per_second": 1.134,
+      "step": 54
+    },
+    {
+      "epoch": 0.0024437927663734115,
+      "grad_norm": 3.0480387210845947,
+      "learning_rate": 5e-05,
+      "loss": 0.8317,
+      "step": 55
+    },
+    {
+      "epoch": 0.0024882253621256556,
+      "grad_norm": 2.246021032333374,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 0.5275,
+      "step": 56
+    },
+    {
+      "epoch": 0.002532657957877899,
+      "grad_norm": 3.443877696990967,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 1.0023,
+      "step": 57
+    },
+    {
+      "epoch": 0.0025770905536301432,
+      "grad_norm": 3.9084110260009766,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.9394,
+      "step": 58
+    },
+    {
+      "epoch": 0.002621523149382387,
+      "grad_norm": 3.4571526050567627,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 1.1275,
+      "step": 59
+    },
+    {
+      "epoch": 0.002665955745134631,
+      "grad_norm": 2.5637829303741455,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.7408,
+      "step": 60
+    },
+    {
+      "epoch": 0.0027103883408868745,
+      "grad_norm": 2.948639154434204,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 0.811,
+      "step": 61
+    },
+    {
+      "epoch": 0.0027548209366391185,
+      "grad_norm": 2.9560561180114746,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 0.6138,
+      "step": 62
+    },
+    {
+      "epoch": 0.002799253532391362,
+      "grad_norm": 2.9435060024261475,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 0.8675,
+      "step": 63
+    },
+    {
+      "epoch": 0.002799253532391362,
+      "eval_loss": 0.8335610628128052,
+      "eval_runtime": 2088.3473,
+      "eval_samples_per_second": 9.076,
+      "eval_steps_per_second": 1.135,
+      "step": 63
+    },
+    {
+      "epoch": 0.002843686128143606,
+      "grad_norm": 1.8505394458770752,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.4345,
+      "step": 64
+    },
+    {
+      "epoch": 0.00288811872389585,
+      "grad_norm": 3.3062446117401123,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 0.9831,
+      "step": 65
+    },
+    {
+      "epoch": 0.002932551319648094,
+      "grad_norm": 3.808541774749756,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.906,
+      "step": 66
+    },
+    {
+      "epoch": 0.002976983915400338,
+      "grad_norm": 3.104768753051758,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 0.9008,
+      "step": 67
+    },
+    {
+      "epoch": 0.0030214165111525815,
+      "grad_norm": 2.730449914932251,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 0.7801,
+      "step": 68
+    },
+    {
+      "epoch": 0.0030658491069048255,
+      "grad_norm": 3.0719079971313477,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 0.623,
+      "step": 69
+    },
+    {
+      "epoch": 0.003110281702657069,
+      "grad_norm": 2.975539445877075,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.9251,
+      "step": 70
+    },
+    {
+      "epoch": 0.003154714298409313,
+      "grad_norm": 2.507993459701538,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 0.5249,
+      "step": 71
+    },
+    {
+      "epoch": 0.003199146894161557,
+      "grad_norm": 2.6667215824127197,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 0.4238,
+      "step": 72
+    },
+    {
+      "epoch": 0.003199146894161557,
+      "eval_loss": 0.8086918592453003,
+      "eval_runtime": 2088.3743,
+      "eval_samples_per_second": 9.075,
+      "eval_steps_per_second": 1.135,
+      "step": 72
+    },
+    {
+      "epoch": 0.003243579489913801,
+      "grad_norm": 2.936882495880127,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.8522,
+      "step": 73
+    },
+    {
+      "epoch": 0.0032880120856660444,
+      "grad_norm": 3.8667545318603516,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 0.8983,
+      "step": 74
+    },
+    {
+      "epoch": 0.0033324446814182885,
+      "grad_norm": 3.9333572387695312,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 1.0196,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.70943641780224e+16,
+  "total_flos": 5.56415462670336e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null