Training in progress, step 1050, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40e24560228e7d2978eabd16e3650531b45d9a750bc9d07e5c6599b62ea323f2
+oid sha256:082057aa43ad4ab7720869b29ef30158762f116e91bb5a5c5ba20dd343d39b13
 size 888392856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62f00fcd6458929b08666bcc1161c1c5bb3616c73b0923ac024450838f886472
+oid sha256:1b5a5de184b932a90ab2a229e1bc76a1cf6ebc20738808f656f5d2e4d0b48c01
 size 1724014074

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:795ff3ab1a3fad7a4fadc5b5b41d290cb0cea6133c8206ce725785c7d25c85ec
+oid sha256:2b3fca934b31e66071a287bca1241ed82b21fe605c83ad79042a2a656622d0a9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afcf237ffb833ad28294e886af7d2dc67a409568829cbb127d7df34e2d3d6579
+oid sha256:d142240d9d34452809b9cf34c6ae579fd7cc4f0b4e78197fa4853e45b45884a6
 size 1256

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.1937243938446045,
   "best_model_checkpoint": "./output/checkpoint-150",
-  "epoch": 0.002053926994306058,
+  "epoch": 0.0023962481600237344,
   "eval_steps": 150,
-  "global_step": 900,
+  "global_step": 1050,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -685,6 +685,119 @@
       "eval_samples_per_second": 11.765,
       "eval_steps_per_second": 11.765,
       "step": 900
+    },
+    {
+      "epoch": 0.002076748405353903,
+      "grad_norm": 61.62263488769531,
+      "learning_rate": 2.0886603661542245e-05,
+      "loss": 1.4012,
+      "step": 910
+    },
+    {
+      "epoch": 0.002099569816401748,
+      "grad_norm": 59.046051025390625,
+      "learning_rate": 2.0850829186663994e-05,
+      "loss": 2.1143,
+      "step": 920
+    },
+    {
+      "epoch": 0.0021223912274495934,
+      "grad_norm": 25.007780075073242,
+      "learning_rate": 2.0814657195847375e-05,
+      "loss": 1.5044,
+      "step": 930
+    },
+    {
+      "epoch": 0.002145212638497438,
+      "grad_norm": 42.121761322021484,
+      "learning_rate": 2.077808917598125e-05,
+      "loss": 1.6489,
+      "step": 940
+    },
+    {
+      "epoch": 0.0021680340495452833,
+      "grad_norm": 62.19163131713867,
+      "learning_rate": 2.0741126630233687e-05,
+      "loss": 1.5162,
+      "step": 950
+    },
+    {
+      "epoch": 0.0021908554605931285,
+      "grad_norm": 25.229106903076172,
+      "learning_rate": 2.070377107799017e-05,
+      "loss": 1.7089,
+      "step": 960
+    },
+    {
+      "epoch": 0.0022136768716409737,
+      "grad_norm": 41.89048385620117,
+      "learning_rate": 2.0666024054791137e-05,
+      "loss": 1.6282,
+      "step": 970
+    },
+    {
+      "epoch": 0.0022364982826888185,
+      "grad_norm": 39.0805549621582,
+      "learning_rate": 2.0627887112268875e-05,
+      "loss": 1.614,
+      "step": 980
+    },
+    {
+      "epoch": 0.0022593196937366637,
+      "grad_norm": 35.681884765625,
+      "learning_rate": 2.0589361818083712e-05,
+      "loss": 2.1457,
+      "step": 990
+    },
+    {
+      "epoch": 0.002282141104784509,
+      "grad_norm": 36.427616119384766,
+      "learning_rate": 2.0550449755859598e-05,
+      "loss": 1.257,
+      "step": 1000
+    },
+    {
+      "epoch": 0.002304962515832354,
+      "grad_norm": 85.96231079101562,
+      "learning_rate": 2.0511152525119014e-05,
+      "loss": 1.6372,
+      "step": 1010
+    },
+    {
+      "epoch": 0.002327783926880199,
+      "grad_norm": 67.32917785644531,
+      "learning_rate": 2.0471471741217183e-05,
+      "loss": 1.4432,
+      "step": 1020
+    },
+    {
+      "epoch": 0.002350605337928044,
+      "grad_norm": 82.99893188476562,
+      "learning_rate": 2.0431409035275724e-05,
+      "loss": 1.925,
+      "step": 1030
+    },
+    {
+      "epoch": 0.002373426748975889,
+      "grad_norm": 79.15724182128906,
+      "learning_rate": 2.0390966054115558e-05,
+      "loss": 1.2961,
+      "step": 1040
+    },
+    {
+      "epoch": 0.0023962481600237344,
+      "grad_norm": 29.493953704833984,
+      "learning_rate": 2.035014446018924e-05,
+      "loss": 1.6837,
+      "step": 1050
+    },
+    {
+      "epoch": 0.0023962481600237344,
+      "eval_loss": 1.3128489255905151,
+      "eval_runtime": 44.2241,
+      "eval_samples_per_second": 11.306,
+      "eval_steps_per_second": 11.306,
+      "step": 1050
     }
   ],
   "logging_steps": 10,
@@ -704,7 +817,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.124423356101376e+16,
+  "total_flos": 3.58409393634432e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null