Training in progress, step 900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c199b9e3b512305005f55eb68da324ab293b3b8950e1f5a272d3930921d33d9b
+oid sha256:0a27a7c2ec6b774731f6aa003dbe657cf0f987fe25d734da3afab88baa02c39d
 size 527048968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b022a2a2d53b6a44873d81b2a118fb3a243719db4c3693bec47989187fe8332
+oid sha256:878dd48bd56764e8178656b692092a26f8627ce77d11d5f9b0b03561a5b8d514
 size 1054135994

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ca9142fcbd976a2b9880762578e5776f18d9cad34016a627060f41ab78ec47d
+oid sha256:e5535f299045fe8f5c903e1fe89ea07c865852a623fd1578e00cbe2ef4b1aa5e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1436fdc963b029d14915fc9410fa4da5908bac7c909f67f4bfe1e0807f32ecef
+oid sha256:6933cf40adb222251144f8b6059d0312a60442b27edead7b2d2d4edd50c35f13
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.7167752981185913,
   "best_model_checkpoint": "./output/checkpoint-450",
-  "epoch": 32.608695652173914,
+  "epoch": 39.130434782608695,
   "eval_steps": 150,
-  "global_step": 750,
+  "global_step": 900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -732,6 +732,151 @@
       "eval_samples_per_second": 25.574,
       "eval_steps_per_second": 25.574,
       "step": 750
+    },
+    {
+      "epoch": 33.04347826086956,
+      "grad_norm": 1.426628589630127,
+      "learning_rate": 1.5787846818616295e-06,
+      "loss": 0.4544,
+      "step": 760
+    },
+    {
+      "epoch": 33.47826086956522,
+      "grad_norm": 1.549428105354309,
+      "learning_rate": 3.157569363723259e-06,
+      "loss": 0.461,
+      "step": 770
+    },
+    {
+      "epoch": 33.91304347826087,
+      "grad_norm": 1.2880816459655762,
+      "learning_rate": 4.736354045584888e-06,
+      "loss": 0.4361,
+      "step": 780
+    },
+    {
+      "epoch": 34.34782608695652,
+      "grad_norm": 1.3904523849487305,
+      "learning_rate": 6.315138727446518e-06,
+      "loss": 0.4367,
+      "step": 790
+    },
+    {
+      "epoch": 34.78260869565217,
+      "grad_norm": 1.4110171794891357,
+      "learning_rate": 7.893923409308147e-06,
+      "loss": 0.4146,
+      "step": 800
+    },
+    {
+      "epoch": 35.21739130434783,
+      "grad_norm": 1.2572520971298218,
+      "learning_rate": 9.472708091169777e-06,
+      "loss": 0.515,
+      "step": 810
+    },
+    {
+      "epoch": 35.65217391304348,
+      "grad_norm": 1.2433037757873535,
+      "learning_rate": 1.1051492773031405e-05,
+      "loss": 0.4429,
+      "step": 820
+    },
+    {
+      "epoch": 36.08695652173913,
+      "grad_norm": 1.068438172340393,
+      "learning_rate": 1.2630277454893036e-05,
+      "loss": 0.4585,
+      "step": 830
+    },
+    {
+      "epoch": 36.52173913043478,
+      "grad_norm": 1.1094129085540771,
+      "learning_rate": 1.4209062136754664e-05,
+      "loss": 0.4247,
+      "step": 840
+    },
+    {
+      "epoch": 36.95652173913044,
+      "grad_norm": 1.3411928415298462,
+      "learning_rate": 1.5787846818616294e-05,
+      "loss": 0.4956,
+      "step": 850
+    },
+    {
+      "epoch": 37.391304347826086,
+      "grad_norm": 1.8016853332519531,
+      "learning_rate": 1.5787845254166782e-05,
+      "loss": 0.4679,
+      "step": 860
+    },
+    {
+      "epoch": 37.82608695652174,
+      "grad_norm": 1.2095096111297607,
+      "learning_rate": 1.5787840560818862e-05,
+      "loss": 0.4155,
+      "step": 870
+    },
+    {
+      "epoch": 38.26086956521739,
+      "grad_norm": 1.1868607997894287,
+      "learning_rate": 1.5787832738574396e-05,
+      "loss": 0.4514,
+      "step": 880
+    },
+    {
+      "epoch": 38.69565217391305,
+      "grad_norm": 1.377031922340393,
+      "learning_rate": 1.5787821787436484e-05,
+      "loss": 0.4023,
+      "step": 890
+    },
+    {
+      "epoch": 39.130434782608695,
+      "grad_norm": 1.88169527053833,
+      "learning_rate": 1.578780770740947e-05,
+      "loss": 0.5221,
+      "step": 900
+    },
+    {
+      "epoch": 39.130434782608695,
+      "eval_loss": 0.7288335561752319,
+      "eval_runtime": 0.4014,
+      "eval_samples_per_second": 24.912,
+      "eval_steps_per_second": 24.912,
+      "step": 900
+    },
+    {
+      "epoch": 39.130434782608695,
+      "eval_loss": 0.8609212040901184,
+      "eval_runtime": 0.5203,
+      "eval_samples_per_second": 19.219,
+      "eval_steps_per_second": 19.219,
+      "step": 900
+    },
+    {
+      "epoch": 39.130434782608695,
+      "eval_loss": 0.7288335561752319,
+      "eval_runtime": 0.5688,
+      "eval_samples_per_second": 17.58,
+      "eval_steps_per_second": 17.58,
+      "step": 900
+    },
+    {
+      "epoch": 39.130434782608695,
+      "eval_loss": 0.7238188982009888,
+      "eval_runtime": 0.4689,
+      "eval_samples_per_second": 21.324,
+      "eval_steps_per_second": 21.324,
+      "step": 900
+    },
+    {
+      "epoch": 39.130434782608695,
+      "eval_loss": 0.861186146736145,
+      "eval_runtime": 0.3946,
+      "eval_samples_per_second": 25.341,
+      "eval_steps_per_second": 25.341,
+      "step": 900
     }
   ],
   "logging_steps": 10,
@@ -751,7 +896,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.9231766387195904e+16,
+  "total_flos": 2.3078822838165504e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null