Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8835860a88bf14bcc1ec2e594b941a5bb0f7bb6734c5a0c063f3998037d3e4a1
+oid sha256:63ed735dadbd535c1c4aad31545c6e04307aae8780e825e413073e798497f71f
 size 104902272

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a920e668115376c5e70d543dfd9d0272ec754edd7754b0ab1d8a885a644da0aa
+oid sha256:2086e7df1454ae8a5cfbc5677d229cfd4127f56fc2a3ce2915f0979c77ff92d0
 size 53622996

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a260fc23bf2aaff0fa034e49ec43c79685a3d848ba4aa240d1b6d96e19d5ae6d
+oid sha256:126be9650908718c7dccc12e5afcd27eab8c4bc940167fe93e88bdc50a27dfc1
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37b24d55a2d45159c3ba7b33757bfd71287a9bc49b6981a8f866e82f021a04d1
+oid sha256:3388a79585db45a863f13723715badd8aa25a52055eaf7b28c440f0e0674ed62
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc1490d9f1c038629cdeb83228f0fc9c05fd7ff6c0ceeb81c9d9648e62aa0002
+oid sha256:dcd73dc5852ad80552fe0290bef22adebe46b96009756d2116377629b0784b69
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff225887629adb84c51ae93f79026be77880d22846880d6b2fab73f5a2d8dde7
+oid sha256:7fe725dc7def59afa6c1fc30d04190e010254a55ef86b07fc304ab67b3c6e386
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b489c13e2d776471e9a48162938854a24466ce6713df9c0fb59abd9a09fb226b
+oid sha256:ca9a25c72339c898b564e0c464a3f6fc75bbeec408008928b7ed05533156b98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04798848276413661,
+  "epoch": 0.06398464368551547,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 65.121,
       "eval_steps_per_second": 8.151,
       "step": 150
+    },
+    {
+      "epoch": 0.05118771494841238,
+      "grad_norm": 4.674208164215088,
+      "learning_rate": 2.0055723659649904e-05,
+      "loss": 4.4265,
+      "step": 160
+    },
+    {
+      "epoch": 0.05438694713268816,
+      "grad_norm": 6.218277454376221,
+      "learning_rate": 1.1454397434679021e-05,
+      "loss": 4.4142,
+      "step": 170
+    },
+    {
+      "epoch": 0.05758617931696393,
+      "grad_norm": 5.0643768310546875,
+      "learning_rate": 5.146355805285452e-06,
+      "loss": 4.5209,
+      "step": 180
+    },
+    {
+      "epoch": 0.0607854115012397,
+      "grad_norm": 4.299080848693848,
+      "learning_rate": 1.2949737362087156e-06,
+      "loss": 4.4362,
+      "step": 190
+    },
+    {
+      "epoch": 0.06398464368551547,
+      "grad_norm": 4.9810404777526855,
+      "learning_rate": 0.0,
+      "loss": 4.3688,
+      "step": 200
+    },
+    {
+      "epoch": 0.06398464368551547,
+      "eval_loss": 1.0858551263809204,
+      "eval_runtime": 80.9167,
+      "eval_samples_per_second": 65.067,
+      "eval_steps_per_second": 8.144,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -158,12 +201,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.680844326178652e+17,
+  "total_flos": 3.5985119241673114e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null