Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9670aa7db7e4681d6bc01c1db491e3559971ab2f7462478636e2d6f526de59bb
+oid sha256:6e6468fbd1dbeca934faa0bb2254394ed0ee8bf8ff125df179e979deb68e590f
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7a3c250f9b7be2bda59d536e362abfdfb6904cb522451643796a1d6ae092841
+oid sha256:cd28020150d2520b3c7b0b1ce18dcef641324e4adb99b1de5db296582483fc3b
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6d6a07809d9337158f5c73e4951e20edf3696427e59806aae7c2879ba180ba7
+oid sha256:e19e9b833f5299be48caa0d664e7fc449683d1a29c985a14772356f242a7b2c0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef527702b4e2147a500c0b29beb26751d245ebb60338b3910b449b6549ac4d59
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.030864197530864196,
+  "epoch": 0.06172839506172839,
   "eval_steps": 8,
-  "global_step": 15,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,57 @@
       "learning_rate": 0.0002,
       "loss": 1.5706,
       "step": 15
+    },
+    {
+      "epoch": 0.03292181069958848,
+      "eval_loss": 1.4741032123565674,
+      "eval_runtime": 42.0815,
+      "eval_samples_per_second": 3.66,
+      "eval_steps_per_second": 1.83,
+      "step": 16
+    },
+    {
+      "epoch": 0.037037037037037035,
+      "grad_norm": 0.21619834005832672,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 1.3482,
+      "step": 18
+    },
+    {
+      "epoch": 0.043209876543209874,
+      "grad_norm": 0.2760312557220459,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.5502,
+      "step": 21
+    },
+    {
+      "epoch": 0.04938271604938271,
+      "grad_norm": 0.22206786274909973,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 1.3306,
+      "step": 24
+    },
+    {
+      "epoch": 0.04938271604938271,
+      "eval_loss": 1.4186367988586426,
+      "eval_runtime": 42.1086,
+      "eval_samples_per_second": 3.657,
+      "eval_steps_per_second": 1.829,
+      "step": 24
+    },
+    {
+      "epoch": 0.05555555555555555,
+      "grad_norm": 0.24945999681949615,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.3103,
+      "step": 27
+    },
+    {
+      "epoch": 0.06172839506172839,
+      "grad_norm": 0.24243028461933136,
+      "learning_rate": 0.0,
+      "loss": 1.2879,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -72,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.396514286993408e+16,
+  "total_flos": 2.7771590934528e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null