Training in progress, step 36, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dd5f0c8fe5d8de2d7c86300e4683230c6f6bdfe172fc1b08a6bb0547632b0ee
+oid sha256:2bd9a0b26c05777e154789f438aca6ab389a4b4e7f14e9e46a64a61ba224e1f9
 size 2264640

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:003e14264bc10d7bf94a2ca481eace96bd4bf67a4383fef49980269dd9687bd6
+oid sha256:f61e2195bb620cac6484901a2dedffd79474f7149b90766f7b4360f25a8ea1b1
 size 1183674

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d25eb66897bc9db464c68a2f7e7d3cb410ee7dcd3fd0e1db4ed0c22dbb4df02
+oid sha256:42c1902870c57878fe9c203bc060ac2f19e644f979d654d1455c49b7c7e2ce2c
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e25540055d73f0c84acced376b2284a3c9b0e959187ff9560a1efc5e7517001
+oid sha256:1e1bd9b6d8210f2244258171cb8c34e568e2483850481e01d45c1d72bc4295d0
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33ef6f4b0dc1a0ee466ac9818efdab5291728661390e42389cd9c4df42291c75
+oid sha256:28651c349f447d90467a1ab072123a42ef3fcd558c7e8a7b853a87ba29324613
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7526132404181185,
+  "epoch": 1.0139372822299653,
   "eval_steps": 9,
-  "global_step": 27,
+  "global_step": 36,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -228,6 +228,77 @@
       "eval_samples_per_second": 191.767,
       "eval_steps_per_second": 48.338,
       "step": 27
+    },
+    {
+      "epoch": 0.7804878048780488,
+      "grad_norm": 0.6679636836051941,
+      "learning_rate": 1.3049554138967051e-05,
+      "loss": 4.5055,
+      "step": 28
+    },
+    {
+      "epoch": 0.8083623693379791,
+      "grad_norm": 0.7194696068763733,
+      "learning_rate": 1.0099138635988026e-05,
+      "loss": 4.5841,
+      "step": 29
+    },
+    {
+      "epoch": 0.8362369337979094,
+      "grad_norm": 0.7062932848930359,
+      "learning_rate": 7.489143213519301e-06,
+      "loss": 4.502,
+      "step": 30
+    },
+    {
+      "epoch": 0.8641114982578397,
+      "grad_norm": 0.7180935740470886,
+      "learning_rate": 5.241835432246889e-06,
+      "loss": 4.4559,
+      "step": 31
+    },
+    {
+      "epoch": 0.89198606271777,
+      "grad_norm": 0.702731192111969,
+      "learning_rate": 3.376388529782215e-06,
+      "loss": 4.6249,
+      "step": 32
+    },
+    {
+      "epoch": 0.9198606271777003,
+      "grad_norm": 0.7095968127250671,
+      "learning_rate": 1.908717841359048e-06,
+      "loss": 4.4653,
+      "step": 33
+    },
+    {
+      "epoch": 0.9477351916376306,
+      "grad_norm": 0.7153111696243286,
+      "learning_rate": 8.513450158049108e-07,
+      "loss": 4.542,
+      "step": 34
+    },
+    {
+      "epoch": 0.975609756097561,
+      "grad_norm": 0.7444437146186829,
+      "learning_rate": 2.1329118524827662e-07,
+      "loss": 4.5022,
+      "step": 35
+    },
+    {
+      "epoch": 1.0139372822299653,
+      "grad_norm": 1.0557011365890503,
+      "learning_rate": 0.0,
+      "loss": 6.8891,
+      "step": 36
+    },
+    {
+      "epoch": 1.0139372822299653,
+      "eval_loss": 4.388754367828369,
+      "eval_runtime": 1.2674,
+      "eval_samples_per_second": 190.94,
+      "eval_steps_per_second": 48.13,
+      "step": 36
     }
   ],
   "logging_steps": 1,
@@ -242,12 +313,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4602071416307712.0,
+  "total_flos": 6149077112717312.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null