Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a61108c9aeb8dbfa4ad2f5e5e7266b18e9f5b3ea73c3440058a938c225792ae
+oid sha256:e158d8231abfabf27daa95080c28c4a83772bf8ff4d41f89a1e66a8411f16beb
 size 17462432

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fc17333ca32240905bdca2b32ddfff631b669996d32bb622b6f819b9869deaa
+oid sha256:569973a3e5a124cf6a66b859203c4dcdbd9b69a89cb9dfbeada6e54e963f9f4c
 size 9114746

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffa705d09861708049cfa2a89b690e3f7f6b7f3df898dfe5690a6c962ec95fba
+oid sha256:906a241dcf8546970aea8f02380e1c2df5213df8101d9bcbcf9de8ff3a87159b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abb650bb9ec91d032de846f0e041bb62d376f579bdffa664965653afe6544978
+oid sha256:7f1b8c119ed37337ec3dea8f96e3af3bb3e6556229f6c151fabee0c7861a44e6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.6234937310218811,
-  "best_model_checkpoint": "checkpoints/checkpoint-100",
-  "epoch": 1.2215384615384615,
+  "best_metric": 0.5491589903831482,
+  "best_model_checkpoint": "checkpoints/checkpoint-200",
+  "epoch": 2.443076923076923,
   "eval_steps": 100,
-  "global_step": 100,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -97,6 +97,96 @@
       "gpu_memory": 4887.19873046875,
       "learning_rate": 0.0002059798494532787,
       "step": 100
+    },
+    {
+      "epoch": 1.3446153846153845,
+      "gpu_memory": 4887.19873046875,
+      "grad_norm": 0.3604443073272705,
+      "learning_rate": 0.00018650913187782535,
+      "loss": 0.8791,
+      "step": 110
+    },
+    {
+      "epoch": 1.4676923076923076,
+      "gpu_memory": 4887.19873046875,
+      "grad_norm": 0.349542498588562,
+      "learning_rate": 0.00016635831825341846,
+      "loss": 0.8584,
+      "step": 120
+    },
+    {
+      "epoch": 1.5907692307692307,
+      "gpu_memory": 4887.19873046875,
+      "grad_norm": 0.3813496232032776,
+      "learning_rate": 0.00014590278011107714,
+      "loss": 0.8552,
+      "step": 130
+    },
+    {
+      "epoch": 1.7138461538461538,
+      "gpu_memory": 4887.19873046875,
+      "grad_norm": 0.3789571225643158,
+      "learning_rate": 0.00012552356542302868,
+      "loss": 0.8731,
+      "step": 140
+    },
+    {
+      "epoch": 1.8369230769230769,
+      "gpu_memory": 4887.19873046875,
+      "grad_norm": 0.3803671896457672,
+      "learning_rate": 0.00010560030039995649,
+      "loss": 0.8411,
+      "step": 150
+    },
+    {
+      "epoch": 1.96,
+      "gpu_memory": 4887.19873046875,
+      "grad_norm": 0.4134896397590637,
+      "learning_rate": 8.650411777297534e-05,
+      "loss": 0.8157,
+      "step": 160
+    },
+    {
+      "epoch": 2.0738461538461537,
+      "gpu_memory": 4887.19873046875,
+      "grad_norm": 0.39426007866859436,
+      "learning_rate": 6.859074329306077e-05,
+      "loss": 0.8023,
+      "step": 170
+    },
+    {
+      "epoch": 2.1969230769230768,
+      "gpu_memory": 4887.19873046875,
+      "grad_norm": 0.3811410367488861,
+      "learning_rate": 5.2193869233367433e-05,
+      "loss": 0.7673,
+      "step": 180
+    },
+    {
+      "epoch": 2.32,
+      "gpu_memory": 4887.19873046875,
+      "grad_norm": 0.37296849489212036,
+      "learning_rate": 3.761893833355035e-05,
+      "loss": 0.7864,
+      "step": 190
+    },
+    {
+      "epoch": 2.443076923076923,
+      "gpu_memory": 4887.19873046875,
+      "grad_norm": 0.45706120133399963,
+      "learning_rate": 2.5137453979444762e-05,
+      "loss": 0.7803,
+      "step": 200
+    },
+    {
+      "epoch": 2.443076923076923,
+      "eval_loss": 0.5491589903831482,
+      "eval_runtime": 0.1999,
+      "eval_samples_per_second": 5.002,
+      "eval_steps_per_second": 5.002,
+      "gpu_memory": 4887.19873046875,
+      "learning_rate": 2.5137453979444762e-05,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -116,7 +206,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.5104035107373056e+16,
+  "total_flos": 3.020807021474611e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null