Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea75b6f915fe653d869d7bffd991f8b73e5fa69cf5112d03e9375b27cab2d882
+oid sha256:62566679ff0b465ec65288c28f43328308d4164cc9dfd2b7762af1bae387b0b2
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c522434e0d48d2883143159fe27d69323fbacf23e2284050dab5f35496013381
+oid sha256:4b0ccb511bd953b0b0f5e903fcc1d8987b1ca825e3c44d5519ce54ff309de579
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c52f7c118f4f94493141b00ccc8987f28f12a1ed9f46dabc17a34ba6b70835b6
+oid sha256:4f7b0cab9943434f797351d01acca9aeceef45c34766451e0220bef9dff17b30
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28418a35cb7e15ebbce37743b08fd366c25ee320167b307a3e449a74781d02de
+oid sha256:439e51f57871ee9c2bc8b35458a0c03f9b948af7a0d15ffe5e1cf9789955c6c8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.042437431991294884,
+  "epoch": 0.0544069640914037,
   "eval_steps": 13,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -312,6 +312,83 @@
       "eval_samples_per_second": 18.653,
       "eval_steps_per_second": 9.35,
       "step": 39
+    },
+    {
+      "epoch": 0.04352557127312296,
+      "grad_norm": 0.20927105844020844,
+      "learning_rate": 7.3223304703363135e-06,
+      "loss": 0.1808,
+      "step": 40
+    },
+    {
+      "epoch": 0.04461371055495103,
+      "grad_norm": 0.19594742357730865,
+      "learning_rate": 5.989850859999227e-06,
+      "loss": 0.1499,
+      "step": 41
+    },
+    {
+      "epoch": 0.04570184983677911,
+      "grad_norm": 0.3185279667377472,
+      "learning_rate": 4.7745751406263165e-06,
+      "loss": 0.2901,
+      "step": 42
+    },
+    {
+      "epoch": 0.046789989118607184,
+      "grad_norm": 0.19601090252399445,
+      "learning_rate": 3.6839958911476957e-06,
+      "loss": 0.1651,
+      "step": 43
+    },
+    {
+      "epoch": 0.04787812840043525,
+      "grad_norm": 0.3092597723007202,
+      "learning_rate": 2.7248368952908053e-06,
+      "loss": 0.1719,
+      "step": 44
+    },
+    {
+      "epoch": 0.04896626768226333,
+      "grad_norm": 0.15384280681610107,
+      "learning_rate": 1.9030116872178316e-06,
+      "loss": 0.13,
+      "step": 45
+    },
+    {
+      "epoch": 0.05005440696409141,
+      "grad_norm": 0.22593477368354797,
+      "learning_rate": 1.2235870926211619e-06,
+      "loss": 0.1633,
+      "step": 46
+    },
+    {
+      "epoch": 0.051142546245919476,
+      "grad_norm": 0.1992155909538269,
+      "learning_rate": 6.907519900580861e-07,
+      "loss": 0.1572,
+      "step": 47
+    },
+    {
+      "epoch": 0.05223068552774755,
+      "grad_norm": 0.21265120804309845,
+      "learning_rate": 3.077914851215585e-07,
+      "loss": 0.1135,
+      "step": 48
+    },
+    {
+      "epoch": 0.05331882480957562,
+      "grad_norm": 0.16999712586402893,
+      "learning_rate": 7.706665667180091e-08,
+      "loss": 0.144,
+      "step": 49
+    },
+    {
+      "epoch": 0.0544069640914037,
+      "grad_norm": 0.2375941425561905,
+      "learning_rate": 0.0,
+      "loss": 0.1357,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -326,12 +403,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6006856471019520.0,
+  "total_flos": 7687956234240000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null