Training in progress, step 34, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe02fc84ee0d1a1e687bcdab29ad9c8fe9b0e9928adc75884a828e38ae419c4e
+oid sha256:39ac7c3a0b9a77ce2d39bed150f09db90896e89fbf3eab095d113daaeeae58a9
 size 156926880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe5d06b25f83bc3a8e5afd1f75f5e49b7dc6a9103080a8b7e4f6d96f89df2b2a
+oid sha256:a72321017d70bd194a8eff4c837dcf70a290a8d49adf7cee6a607a200ecb00c4
 size 313998650

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e434730fd744be2adc90451f3ccacc9e2a75315837a97354fe29b5bebc5edde
+oid sha256:90023084121c65e806bf421869e2595238b795638d0aef44c1775966ffab8018
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60e34914aa5232eef20f19659268c9dfa47886d59e654a16973465c9faa9a763
+oid sha256:3d1de72c4aa987061e43ffd8007384d58d7baef5e7de8fd0a43a862305fa86fa
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28c46d0a1fb0d1f9ac747df4db674067ac54d33f535eac56b8b89f0ff8c7fd0b
+oid sha256:7a9445e6065a43639b1c98786f7474ac222dd620a0cbd4bcc7f15a58d0ca8a02
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9302c1a4300a0a2430ded27ca752df578b15495a716a3ca81fee2b8e7b1ead52
+oid sha256:1a32172f1713564da9ca60c6f51605fa3e540639f35d8e82d472c2d9b6bb90cc
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c220d2fbe9a2870f9ac93749b3d4b3852ce94b5983d948fa8de3d35e453f98ce
+oid sha256:7312f49c1e1b01f68cdaee175129535fda49cd22ed1f251a2745d2c8c42996be
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.2598870056497176,
+  "epoch": 3.073446327683616,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 34,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,69 @@
       "eval_samples_per_second": 33.704,
       "eval_steps_per_second": 8.763,
       "step": 25
+    },
+    {
+      "epoch": 2.3502824858757063,
+      "grad_norm": 1.6147388219833374,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.3578,
+      "step": 26
+    },
+    {
+      "epoch": 2.440677966101695,
+      "grad_norm": 0.581788182258606,
+      "learning_rate": 2.0214529598676836e-05,
+      "loss": 0.3577,
+      "step": 27
+    },
+    {
+      "epoch": 2.5310734463276834,
+      "grad_norm": 1.152259111404419,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.3402,
+      "step": 28
+    },
+    {
+      "epoch": 2.621468926553672,
+      "grad_norm": 0.992540717124939,
+      "learning_rate": 1.531354310432403e-05,
+      "loss": 0.3486,
+      "step": 29
+    },
+    {
+      "epoch": 2.711864406779661,
+      "grad_norm": 1.0127880573272705,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.3496,
+      "step": 30
+    },
+    {
+      "epoch": 2.8022598870056497,
+      "grad_norm": 0.23949310183525085,
+      "learning_rate": 1.1937684892050604e-05,
+      "loss": 0.3407,
+      "step": 31
+    },
+    {
+      "epoch": 2.8926553672316384,
+      "grad_norm": 0.46344828605651855,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.3595,
+      "step": 32
+    },
+    {
+      "epoch": 2.983050847457627,
+      "grad_norm": 0.9140104651451111,
+      "learning_rate": 1.0216687299751144e-05,
+      "loss": 0.3471,
+      "step": 33
+    },
+    {
+      "epoch": 3.073446327683616,
+      "grad_norm": 1.3315057754516602,
+      "learning_rate": 1e-05,
+      "loss": 0.6613,
+      "step": 34
     }
   ],
   "logging_steps": 1,
@@ -212,12 +275,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7.94731890081792e+16,
+  "total_flos": 1.0808353705112371e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null