Training in progress, step 288, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc55da3a89171bf252e042ada42565e064487a2157541887e69eac3d97d442b2
+oid sha256:3c710d5308aaf807b393268e891181fdcf0a83b0d3dc6b61a24c016445870811
 size 201892112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da2d2119e83f390d39071b1ec721709219117ccbb0dd644e82b4474f317dcb14
+oid sha256:572f4d4fba72b5138433a2330c55a602658ac5035922c0d898879a677b600613
 size 102864868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e1bd3ac95599b40f1305be1f0a64cd545e152ad7b38b9a60045306725bab973
+oid sha256:87a700122aca445dc8ce412f4c11381ecd21f57c059d16669dbcf5041a39941e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93ded0d5cb9245a05d18914685d015def341481d1dc23b96d02a9408efc885cf
+oid sha256:1e33148aad92ddf4c03cb81316d9ace5fb35dc75321bc8a095c2633bf9c47595
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.75,
+  "epoch": 3.0,
   "eval_steps": 24,
-  "global_step": 264,
+  "global_step": 288,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -719,6 +719,70 @@
       "eval_samples_per_second": 48.591,
       "eval_steps_per_second": 6.299,
       "step": 264
+    },
+    {
+      "epoch": 2.78125,
+      "grad_norm": 0.48225662112236023,
+      "learning_rate": 7.006797640922436e-07,
+      "loss": 1.3077,
+      "step": 267
+    },
+    {
+      "epoch": 2.8125,
+      "grad_norm": 0.4646640419960022,
+      "learning_rate": 5.154270296314878e-07,
+      "loss": 1.2931,
+      "step": 270
+    },
+    {
+      "epoch": 2.84375,
+      "grad_norm": 0.5893747210502625,
+      "learning_rate": 3.583129673691427e-07,
+      "loss": 1.3327,
+      "step": 273
+    },
+    {
+      "epoch": 2.875,
+      "grad_norm": 0.601911723613739,
+      "learning_rate": 2.295181392084511e-07,
+      "loss": 1.3169,
+      "step": 276
+    },
+    {
+      "epoch": 2.90625,
+      "grad_norm": 0.5594666600227356,
+      "learning_rate": 1.2919056143113062e-07,
+      "loss": 1.3379,
+      "step": 279
+    },
+    {
+      "epoch": 2.9375,
+      "grad_norm": 0.5165249705314636,
+      "learning_rate": 5.7445534591002436e-08,
+      "loss": 1.3493,
+      "step": 282
+    },
+    {
+      "epoch": 2.96875,
+      "grad_norm": 0.48071709275245667,
+      "learning_rate": 1.4365511005878795e-08,
+      "loss": 1.3008,
+      "step": 285
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.5523079037666321,
+      "learning_rate": 0.0,
+      "loss": 1.3255,
+      "step": 288
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.3729829788208008,
+      "eval_runtime": 3.3405,
+      "eval_samples_per_second": 48.496,
+      "eval_steps_per_second": 6.287,
+      "step": 288
     }
   ],
   "logging_steps": 3,
@@ -733,12 +797,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5.959481812844544e+16,
+  "total_flos": 6.472770514845696e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null