Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,9 +20,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "dense_4h_to_h",
     "query_key_value",
     "dense",
-    "dense_4h_to_h",
     "dense_h_to_4h"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cc1e787ee26b6d7c3c2f429bb7b9d84ded25a37e7a6ca02c50e7912a1c24f4d
+oid sha256:631776cd4c25e545085ceaaed92331ecaf69974355b8b1f4276ff3c7d505367b
 size 65309632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b53462429da2d4b52940f8a4bd79816162f9a85434691c9d1f793c1457bf925
+oid sha256:e05a66adc844a3d718485516b4d523d8142abd1e42ccd75f7ff21e1dd3b78853
 size 33424212

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7224737c5fc069bc4257b111eb6b8611d5a8c6fec9f5de5d1c0c49e0f45eab66
+oid sha256:f918e894c61d79473825b52a272cf41e854c27a6d9183f7c13da913c2b3b6227
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
+oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.963051441312311e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0010351966873706005,
+  "eval_steps": 10,
+  "global_step": 13,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,17 +11,39 @@
     {
       "epoch": 7.963051441312311e-05,
       "eval_loss": 0.8125210404396057,
-      "eval_runtime": 439.9632,
-      "eval_samples_per_second": 12.019,
-      "eval_steps_per_second": 6.01,
+      "eval_runtime": 440.94,
+      "eval_samples_per_second": 11.993,
+      "eval_steps_per_second": 5.996,
       "step": 1
+    },
+    {
+      "epoch": 0.00039815257206561556,
+      "grad_norm": 1.3683063983917236,
+      "learning_rate": 5e-05,
+      "loss": 3.1714,
+      "step": 5
+    },
+    {
+      "epoch": 0.0007963051441312311,
+      "grad_norm": 2.482180595397949,
+      "learning_rate": 0.0001,
+      "loss": 2.9685,
+      "step": 10
+    },
+    {
+      "epoch": 0.0007963051441312311,
+      "eval_loss": 0.5994144678115845,
+      "eval_runtime": 450.0496,
+      "eval_samples_per_second": 11.75,
+      "eval_steps_per_second": 5.875,
+      "step": 10
     }
   ],
   "logging_steps": 5,
-  "max_steps": 1,
+  "max_steps": 50,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
-  "save_steps": 1,
+  "save_steps": 13,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -29,12 +51,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 163247803072512.0,
+  "total_flos": 2122221439942656.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11660531384bc8a2578ea88a5187dada79fb5a40311e453fa7254e6acdf1c34f
+oid sha256:badef1aba23736e1fafcd81d162fb2e2e3e58f49a52fa2f0a85eced98f12627f
 size 6776