Training in progress, step 2400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe945d679deecbd7e8f1bf3f6218e8071999cc48891a5cc26c87950cbf8ce49b
+oid sha256:6f09644560ff21c0cac0dc280c2e5a17b51797de861561d39016c4a93cb2ecfc
 size 101752088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbd4f0c6005622c69470043161d8ddd8639be3e6da6538cc0549895d966884a8
+oid sha256:3f5fbc165c90fc400193733f2f4ec0de9bb66ad7ce5d2623ea31301c3c843aa8
 size 203719079

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b980a66b6e57f076f69807f45a48b45a7f943415f47c6d25a6395314cf209e0d
+oid sha256:d89f11a61cdbf936e1922f1f4c1975dcbb372c36c7df8bb6932c03cf9e94d69c
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb0f627823758704b99c0100536ff12ee5c39e3502f9f5e2784e258e698a30f7
+oid sha256:2a55f3acde6dde848ed30d866c5a5ff7da6af4cd03cbfab7f1dfd0c0dc9eb6a4
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.33264691905591637,
+  "epoch": 0.38016790749247587,
   "eval_steps": 500,
-  "global_step": 2100,
+  "global_step": 2400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1478,6 +1478,216 @@
       "learning_rate": 2.505040022749265e-05,
       "loss": 1.2165,
       "step": 2100
+    },
+    {
+      "epoch": 0.3342309520038017,
+      "grad_norm": 1.0949828624725342,
+      "learning_rate": 2.4547929212481435e-05,
+      "loss": 1.2863,
+      "step": 2110
+    },
+    {
+      "epoch": 0.335814984951687,
+      "grad_norm": 0.6609100103378296,
+      "learning_rate": 2.404890400043023e-05,
+      "loss": 1.2751,
+      "step": 2120
+    },
+    {
+      "epoch": 0.33739901789957233,
+      "grad_norm": 0.7404264807701111,
+      "learning_rate": 2.3553392151364536e-05,
+      "loss": 1.3004,
+      "step": 2130
+    },
+    {
+      "epoch": 0.3389830508474576,
+      "grad_norm": 0.8399338722229004,
+      "learning_rate": 2.3061460749656844e-05,
+      "loss": 1.4249,
+      "step": 2140
+    },
+    {
+      "epoch": 0.34056708379534295,
+      "grad_norm": 0.9257438778877258,
+      "learning_rate": 2.2573176394944328e-05,
+      "loss": 1.4161,
+      "step": 2150
+    },
+    {
+      "epoch": 0.34215111674322823,
+      "grad_norm": 0.8689798712730408,
+      "learning_rate": 2.2088605193112383e-05,
+      "loss": 1.2699,
+      "step": 2160
+    },
+    {
+      "epoch": 0.3437351496911136,
+      "grad_norm": 0.7370318174362183,
+      "learning_rate": 2.160781274734495e-05,
+      "loss": 1.3336,
+      "step": 2170
+    },
+    {
+      "epoch": 0.3453191826389989,
+      "grad_norm": 0.7378177046775818,
+      "learning_rate": 2.1130864149242878e-05,
+      "loss": 1.3478,
+      "step": 2180
+    },
+    {
+      "epoch": 0.3469032155868842,
+      "grad_norm": 0.7509024143218994,
+      "learning_rate": 2.0657823970011618e-05,
+      "loss": 1.3091,
+      "step": 2190
+    },
+    {
+      "epoch": 0.34848724853476953,
+      "grad_norm": 0.7333298921585083,
+      "learning_rate": 2.0188756251719203e-05,
+      "loss": 1.3382,
+      "step": 2200
+    },
+    {
+      "epoch": 0.3500712814826548,
+      "grad_norm": 0.729038655757904,
+      "learning_rate": 1.9723724498626105e-05,
+      "loss": 1.2599,
+      "step": 2210
+    },
+    {
+      "epoch": 0.35165531443054016,
+      "grad_norm": 1.0300594568252563,
+      "learning_rate": 1.9262791668587676e-05,
+      "loss": 1.332,
+      "step": 2220
+    },
+    {
+      "epoch": 0.3532393473784255,
+      "grad_norm": 1.1736242771148682,
+      "learning_rate": 1.8806020164530702e-05,
+      "loss": 1.2849,
+      "step": 2230
+    },
+    {
+      "epoch": 0.3548233803263108,
+      "grad_norm": 0.758115828037262,
+      "learning_rate": 1.8353471826005036e-05,
+      "loss": 1.4054,
+      "step": 2240
+    },
+    {
+      "epoch": 0.3564074132741961,
+      "grad_norm": 0.9238961935043335,
+      "learning_rate": 1.7905207920811572e-05,
+      "loss": 1.4045,
+      "step": 2250
+    },
+    {
+      "epoch": 0.3579914462220814,
+      "grad_norm": 0.8140641450881958,
+      "learning_rate": 1.746128913670746e-05,
+      "loss": 1.3212,
+      "step": 2260
+    },
+    {
+      "epoch": 0.35957547916996674,
+      "grad_norm": 0.690086305141449,
+      "learning_rate": 1.7021775573190013e-05,
+      "loss": 1.3071,
+      "step": 2270
+    },
+    {
+      "epoch": 0.3611595121178521,
+      "grad_norm": 0.7119179368019104,
+      "learning_rate": 1.6586726733360237e-05,
+      "loss": 1.1963,
+      "step": 2280
+    },
+    {
+      "epoch": 0.36274354506573736,
+      "grad_norm": 0.90193772315979,
+      "learning_rate": 1.615620151586697e-05,
+      "loss": 1.3169,
+      "step": 2290
+    },
+    {
+      "epoch": 0.3643275780136227,
+      "grad_norm": 0.791403591632843,
+      "learning_rate": 1.5730258206933025e-05,
+      "loss": 1.3956,
+      "step": 2300
+    },
+    {
+      "epoch": 0.365911610961508,
+      "grad_norm": 0.9166008234024048,
+      "learning_rate": 1.530895447246411e-05,
+      "loss": 1.2468,
+      "step": 2310
+    },
+    {
+      "epoch": 0.3674956439093933,
+      "grad_norm": 0.8105589151382446,
+      "learning_rate": 1.4892347350241881e-05,
+      "loss": 1.2856,
+      "step": 2320
+    },
+    {
+      "epoch": 0.3690796768572786,
+      "grad_norm": 0.7731050252914429,
+      "learning_rate": 1.448049324220181e-05,
+      "loss": 1.32,
+      "step": 2330
+    },
+    {
+      "epoch": 0.37066370980516394,
+      "grad_norm": 0.6832409501075745,
+      "learning_rate": 1.4073447906797376e-05,
+      "loss": 1.4165,
+      "step": 2340
+    },
+    {
+      "epoch": 0.3722477427530493,
+      "grad_norm": 0.7237154841423035,
+      "learning_rate": 1.367126645145121e-05,
+      "loss": 1.3432,
+      "step": 2350
+    },
+    {
+      "epoch": 0.37383177570093457,
+      "grad_norm": 0.8293668031692505,
+      "learning_rate": 1.327400332509442e-05,
+      "loss": 1.3723,
+      "step": 2360
+    },
+    {
+      "epoch": 0.3754158086488199,
+      "grad_norm": 0.9197924733161926,
+      "learning_rate": 1.2881712310795118e-05,
+      "loss": 1.2893,
+      "step": 2370
+    },
+    {
+      "epoch": 0.3769998415967052,
+      "grad_norm": 0.725936233997345,
+      "learning_rate": 1.2494446518477022e-05,
+      "loss": 1.2668,
+      "step": 2380
+    },
+    {
+      "epoch": 0.3785838745445905,
+      "grad_norm": 0.768979012966156,
+      "learning_rate": 1.2112258377729274e-05,
+      "loss": 1.347,
+      "step": 2390
+    },
+    {
+      "epoch": 0.38016790749247587,
+      "grad_norm": 0.7712375521659851,
+      "learning_rate": 1.1735199630708222e-05,
+      "loss": 1.2925,
+      "step": 2400
     }
   ],
   "logging_steps": 10,
@@ -1497,7 +1707,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.91465321709568e+17,
+  "total_flos": 7.90246081953792e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null