Training in progress, step 1600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cde203de07c94321f404b467390aa4462b08af57f964af982ca0026ee674c5f
+oid sha256:0f32570245fc0f5f78747c1de78650be46a1ea3b8e729729e94bf24de0a0bfbc
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61fc6f4f10033236de6b35c3b0dc8eb4ae66ac1585aa6168a450441198fbb2be
+oid sha256:09a745a2ac74049b033be5cbf534119d0c44c4d6546507e0be8150df70148ad1
 size 70668243

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fc94c84524322ebd51cda43c9690237200523c4dd3dd246d0524b37a62c0a7a
+oid sha256:dd148f566dd3c978e2c35bad1068345ff1646fb64d0652c912316b941bfb6fa3
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:555b991c201c24ca09a4cb1ca6783e2831260c942d84bd207916634e8ab3861c
+oid sha256:bc729bd438ef943a7f288d289009e4e1f08da4e3a4b1aa9af9af0e106c622bb7
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.1963369963369965,
+  "epoch": 2.342857142857143,
   "eval_steps": 100,
-  "global_step": 1500,
+  "global_step": 1600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1178,6 +1178,84 @@
       "eval_samples_per_second": 11.054,
       "eval_steps_per_second": 5.527,
       "step": 1500
+    },
+    {
+      "epoch": 2.210989010989011,
+      "grad_norm": 0.3285888731479645,
+      "learning_rate": 3.4286108858335876e-05,
+      "loss": 0.0151,
+      "step": 1510
+    },
+    {
+      "epoch": 2.2256410256410257,
+      "grad_norm": 0.1767551451921463,
+      "learning_rate": 3.3102607070085434e-05,
+      "loss": 0.0134,
+      "step": 1520
+    },
+    {
+      "epoch": 2.2402930402930403,
+      "grad_norm": 0.20652097463607788,
+      "learning_rate": 3.193582789552536e-05,
+      "loss": 0.0161,
+      "step": 1530
+    },
+    {
+      "epoch": 2.254945054945055,
+      "grad_norm": 0.2954496741294861,
+      "learning_rate": 3.078606299919655e-05,
+      "loss": 0.0125,
+      "step": 1540
+    },
+    {
+      "epoch": 2.2695970695970695,
+      "grad_norm": 0.16948480904102325,
+      "learning_rate": 2.9653599792511565e-05,
+      "loss": 0.0128,
+      "step": 1550
+    },
+    {
+      "epoch": 2.284249084249084,
+      "grad_norm": 0.102840356528759,
+      "learning_rate": 2.853872136190907e-05,
+      "loss": 0.0134,
+      "step": 1560
+    },
+    {
+      "epoch": 2.2989010989010987,
+      "grad_norm": 0.3079432249069214,
+      "learning_rate": 2.744170639808973e-05,
+      "loss": 0.0171,
+      "step": 1570
+    },
+    {
+      "epoch": 2.3135531135531133,
+      "grad_norm": 0.27339795231819153,
+      "learning_rate": 2.6362829126350662e-05,
+      "loss": 0.0138,
+      "step": 1580
+    },
+    {
+      "epoch": 2.3282051282051284,
+      "grad_norm": 0.31931355595588684,
+      "learning_rate": 2.5302359238036233e-05,
+      "loss": 0.0148,
+      "step": 1590
+    },
+    {
+      "epoch": 2.342857142857143,
+      "grad_norm": 0.13978998363018036,
+      "learning_rate": 2.4260561823122254e-05,
+      "loss": 0.0132,
+      "step": 1600
+    },
+    {
+      "epoch": 2.342857142857143,
+      "eval_loss": 0.021637454628944397,
+      "eval_runtime": 4.5371,
+      "eval_samples_per_second": 11.02,
+      "eval_steps_per_second": 5.51,
+      "step": 1600
     }
   ],
   "logging_steps": 10,
@@ -1197,7 +1275,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6529071981158400.0,
+  "total_flos": 6967642246663680.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null