Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6097bcaa7ebc4d5338f0c8291ea1c8ba9d8dc1728c6cd3ce1abc6b2496599da
+oid sha256:92baf6c605f92e8b5e551def327c222b45c12563a07ccf3a5f1870792f173b2c
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae733c3f0e030b67899bc7cfbf9af2c544ec06232139446de9a52425a6616306
+oid sha256:3aa3f3134767a2579b748a96abff482772e062cbef282320ab2a2ac6456f26a9
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48b571a1cda1c18e0b76f3cd6c89bae53eb9d1241ef187c71a1c58bcd4925246
+oid sha256:bf7884caf161c2ce1c9ec67b264a8b146600888d6f011a86ff7659e220ad4974
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d914dc409ae93ac75985631a9974025ebaa397f621307eef226e7d6e1076a1f6
+oid sha256:babd43118aa66a4f5266d730539cf7f09611158b169d9e63dbcb83f6bbaa8626
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.17323516673884798,
+  "epoch": 0.25985275010827197,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,189 @@
       "eval_samples_per_second": 4.415,
       "eval_steps_per_second": 2.208,
       "step": 50
+    },
+    {
+      "epoch": 0.17669987007362495,
+      "grad_norm": 35.518733978271484,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 3.7489,
+      "step": 51
+    },
+    {
+      "epoch": 0.18016457340840192,
+      "grad_norm": 13.69632625579834,
+      "learning_rate": 4.6270039165317605e-05,
+      "loss": 3.3506,
+      "step": 52
+    },
+    {
+      "epoch": 0.18362927674317886,
+      "grad_norm": 8.78832721710205,
+      "learning_rate": 4.264235636489542e-05,
+      "loss": 1.1164,
+      "step": 53
+    },
+    {
+      "epoch": 0.18709398007795583,
+      "grad_norm": 19.308809280395508,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 2.4321,
+      "step": 54
+    },
+    {
+      "epoch": 0.19055868341273277,
+      "grad_norm": 37.123531341552734,
+      "learning_rate": 3.5721239031346066e-05,
+      "loss": 2.8694,
+      "step": 55
+    },
+    {
+      "epoch": 0.19402338674750974,
+      "grad_norm": 17.861862182617188,
+      "learning_rate": 3.244097923843398e-05,
+      "loss": 2.7996,
+      "step": 56
+    },
+    {
+      "epoch": 0.1974880900822867,
+      "grad_norm": 25.85512351989746,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 3.5098,
+      "step": 57
+    },
+    {
+      "epoch": 0.20095279341706365,
+      "grad_norm": 15.257984161376953,
+      "learning_rate": 2.6272266318987603e-05,
+      "loss": 4.2756,
+      "step": 58
+    },
+    {
+      "epoch": 0.20441749675184062,
+      "grad_norm": 9.036160469055176,
+      "learning_rate": 2.339555568810221e-05,
+      "loss": 2.1725,
+      "step": 59
+    },
+    {
+      "epoch": 0.2078822000866176,
+      "grad_norm": 8.915935516357422,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 2.2972,
+      "step": 60
+    },
+    {
+      "epoch": 0.21134690342139453,
+      "grad_norm": 21.377731323242188,
+      "learning_rate": 1.808479557110081e-05,
+      "loss": 3.7501,
+      "step": 61
+    },
+    {
+      "epoch": 0.2148116067561715,
+      "grad_norm": 25.860002517700195,
+      "learning_rate": 1.566085541871145e-05,
+      "loss": 4.4689,
+      "step": 62
+    },
+    {
+      "epoch": 0.21827631009094847,
+      "grad_norm": 18.97432518005371,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 1.9634,
+      "step": 63
+    },
+    {
+      "epoch": 0.22174101342572541,
+      "grad_norm": 19.91278839111328,
+      "learning_rate": 1.129891668217783e-05,
+      "loss": 2.4683,
+      "step": 64
+    },
+    {
+      "epoch": 0.22520571676050238,
+      "grad_norm": 23.109867095947266,
+      "learning_rate": 9.369221296335006e-06,
+      "loss": 5.7752,
+      "step": 65
+    },
+    {
+      "epoch": 0.22867042009527935,
+      "grad_norm": 15.709304809570312,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 3.541,
+      "step": 66
+    },
+    {
+      "epoch": 0.2321351234300563,
+      "grad_norm": 20.902395248413086,
+      "learning_rate": 6.030737921409169e-06,
+      "loss": 3.8023,
+      "step": 67
+    },
+    {
+      "epoch": 0.23559982676483326,
+      "grad_norm": 23.645151138305664,
+      "learning_rate": 4.628304925177318e-06,
+      "loss": 3.0177,
+      "step": 68
+    },
+    {
+      "epoch": 0.23906453009961023,
+      "grad_norm": 17.126794815063477,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 2.0654,
+      "step": 69
+    },
+    {
+      "epoch": 0.24252923343438718,
+      "grad_norm": 20.345962524414062,
+      "learning_rate": 2.3703992880066638e-06,
+      "loss": 3.7378,
+      "step": 70
+    },
+    {
+      "epoch": 0.24599393676916415,
+      "grad_norm": 21.93646812438965,
+      "learning_rate": 1.5192246987791981e-06,
+      "loss": 2.4299,
+      "step": 71
+    },
+    {
+      "epoch": 0.2494586401039411,
+      "grad_norm": 20.879924774169922,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 2.5581,
+      "step": 72
+    },
+    {
+      "epoch": 0.2529233434387181,
+      "grad_norm": 31.036603927612305,
+      "learning_rate": 3.805301908254455e-07,
+      "loss": 4.7284,
+      "step": 73
+    },
+    {
+      "epoch": 0.256388046773495,
+      "grad_norm": 24.942869186401367,
+      "learning_rate": 9.517784181422019e-08,
+      "loss": 2.1838,
+      "step": 74
+    },
+    {
+      "epoch": 0.25985275010827197,
+      "grad_norm": 11.447266578674316,
+      "learning_rate": 0.0,
+      "loss": 2.1105,
+      "step": 75
+    },
+    {
+      "epoch": 0.25985275010827197,
+      "eval_loss": 0.38869383931159973,
+      "eval_runtime": 55.2151,
+      "eval_samples_per_second": 4.419,
+      "eval_steps_per_second": 2.21,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -395,12 +578,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.2695579394048e+17,
+  "total_flos": 1.9043369091072e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null