Training in progress, step 600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65656f427a8c1b2c852eb04065a03dc8e05637db3b50b5d4ae72991160e67bce
+oid sha256:ac57e1708ae96d8a754b239e7a24dcbc95bfc8819c0cb304a4d5463df3d9f1e9
 size 527048968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e48ae36804c8c5bd040576f72a1c35dc67307237858a4a6849ca6da8a7f3345
+oid sha256:0891e5d321b6e79898a6903d5e687dcf1984e09c5c630de43f20284ed62709e4
 size 1054135994

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f76c4c2dca19bfb0a463693a0e409b44510488650d816e566bccd2a2851e9524
+oid sha256:b3db7d037567f9907c679104cc622f6046bdf2f33143ca3a29365b2fa4072ce8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da0b9a1e2fa3da24e9af8b74787d70ff4c95d9bc9b74eeab135df0350a00b462
+oid sha256:3a6a671e7a99b2031fac9c2aa2961bdd45065beec21991b71e40498a79f90a5d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.7168284058570862,
   "best_model_checkpoint": "./output/checkpoint-450",
-  "epoch": 19.565217391304348,
+  "epoch": 26.08695652173913,
   "eval_steps": 150,
-  "global_step": 450,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -442,6 +442,151 @@
       "eval_samples_per_second": 24.487,
       "eval_steps_per_second": 24.487,
       "step": 450
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 2.1195826530456543,
+      "learning_rate": 2.9996147467351856e-05,
+      "loss": 0.5146,
+      "step": 460
+    },
+    {
+      "epoch": 20.434782608695652,
+      "grad_norm": 1.268523097038269,
+      "learning_rate": 2.9995930474939773e-05,
+      "loss": 0.4781,
+      "step": 470
+    },
+    {
+      "epoch": 20.869565217391305,
+      "grad_norm": 1.4743558168411255,
+      "learning_rate": 2.9995707538619975e-05,
+      "loss": 0.5705,
+      "step": 480
+    },
+    {
+      "epoch": 21.304347826086957,
+      "grad_norm": 1.3239866495132446,
+      "learning_rate": 2.9995478658480822e-05,
+      "loss": 0.5163,
+      "step": 490
+    },
+    {
+      "epoch": 21.73913043478261,
+      "grad_norm": 1.2419785261154175,
+      "learning_rate": 2.9995243834613043e-05,
+      "loss": 0.5205,
+      "step": 500
+    },
+    {
+      "epoch": 22.17391304347826,
+      "grad_norm": 1.7764437198638916,
+      "learning_rate": 2.9995003067109707e-05,
+      "loss": 0.4838,
+      "step": 510
+    },
+    {
+      "epoch": 22.608695652173914,
+      "grad_norm": 1.5313807725906372,
+      "learning_rate": 2.9994756356066246e-05,
+      "loss": 0.5616,
+      "step": 520
+    },
+    {
+      "epoch": 23.043478260869566,
+      "grad_norm": 1.7396149635314941,
+      "learning_rate": 2.999450370158046e-05,
+      "loss": 0.4929,
+      "step": 530
+    },
+    {
+      "epoch": 23.47826086956522,
+      "grad_norm": 1.310137152671814,
+      "learning_rate": 2.9994245103752478e-05,
+      "loss": 0.4385,
+      "step": 540
+    },
+    {
+      "epoch": 23.91304347826087,
+      "grad_norm": 1.2314122915267944,
+      "learning_rate": 2.999398056268481e-05,
+      "loss": 0.5265,
+      "step": 550
+    },
+    {
+      "epoch": 24.347826086956523,
+      "grad_norm": 1.405901312828064,
+      "learning_rate": 2.9993710078482306e-05,
+      "loss": 0.5203,
+      "step": 560
+    },
+    {
+      "epoch": 24.782608695652176,
+      "grad_norm": 0.9515899419784546,
+      "learning_rate": 2.9993433651252185e-05,
+      "loss": 0.443,
+      "step": 570
+    },
+    {
+      "epoch": 25.217391304347824,
+      "grad_norm": 1.7217934131622314,
+      "learning_rate": 2.9993151281104006e-05,
+      "loss": 0.5327,
+      "step": 580
+    },
+    {
+      "epoch": 25.652173913043477,
+      "grad_norm": 1.1352386474609375,
+      "learning_rate": 2.9992862968149695e-05,
+      "loss": 0.4737,
+      "step": 590
+    },
+    {
+      "epoch": 26.08695652173913,
+      "grad_norm": 1.1713489294052124,
+      "learning_rate": 2.9992568712503533e-05,
+      "loss": 0.4607,
+      "step": 600
+    },
+    {
+      "epoch": 26.08695652173913,
+      "eval_loss": 0.7201142311096191,
+      "eval_runtime": 0.4104,
+      "eval_samples_per_second": 24.369,
+      "eval_steps_per_second": 24.369,
+      "step": 600
+    },
+    {
+      "epoch": 26.08695652173913,
+      "eval_loss": 0.8616224527359009,
+      "eval_runtime": 0.4009,
+      "eval_samples_per_second": 24.945,
+      "eval_steps_per_second": 24.945,
+      "step": 600
+    },
+    {
+      "epoch": 26.08695652173913,
+      "eval_loss": 0.7201142311096191,
+      "eval_runtime": 0.3978,
+      "eval_samples_per_second": 25.14,
+      "eval_steps_per_second": 25.14,
+      "step": 600
+    },
+    {
+      "epoch": 26.08695652173913,
+      "eval_loss": 0.7344290018081665,
+      "eval_runtime": 0.3994,
+      "eval_samples_per_second": 25.038,
+      "eval_steps_per_second": 25.038,
+      "step": 600
+    },
+    {
+      "epoch": 26.08695652173913,
+      "eval_loss": 0.8599739074707031,
+      "eval_runtime": 0.3997,
+      "eval_samples_per_second": 25.02,
+      "eval_steps_per_second": 25.02,
+      "step": 600
     }
   ],
   "logging_steps": 10,
@@ -461,7 +606,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1591800814075904e+16,
+  "total_flos": 1.5363065839583232e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null