Training in progress, step 3, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "v_proj",
     "gate_proj",
     "up_proj",
-    "o_proj",
     "down_proj",
-    "q_proj"
+    "v_proj",
+    "o_proj",
+    "q_proj",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e84e6655860f61503b7d47ec6b1e4dc1058eb537961ecaff8375b345098e329c
+oid sha256:40d29df0640c7c8a75785834b0e3f0a3530040e0046fc70187348cdc741331d6
 size 42002136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1eea2e1d1b68c64890a7e2c44e709ce8e79b03e7f500b53da9cef6ba48ce6457
+oid sha256:1e60f719732af575b3234320190d79528ec584ecb4cba697496af83b8ec3f060
 size 21822612

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b0bee0f47e046288a8ab410015fc2b2510b7d505ae807cb056407e3f2c1143e
+oid sha256:599c2ea671aca755731f34991ceda78bd2524adf64429255d5c07acbd8db3fc1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
 size 1064

last-checkpoint/trainer_state.json

@@ -1,16 +1,16 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04201680672268908,
+  "epoch": 0.012605042016806723,
   "eval_steps": 3,
-  "global_step": 10,
+  "global_step": 3,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.004201680672268907,
-      "grad_norm": 8.23998737335205,
+      "grad_norm": 8.212823867797852,
       "learning_rate": 2e-05,
       "loss": 1.6141,
       "step": 1
@@ -18,97 +18,32 @@
     {
       "epoch": 0.004201680672268907,
       "eval_loss": 1.1479942798614502,
-      "eval_runtime": 1.7165,
-      "eval_samples_per_second": 7.574,
-      "eval_steps_per_second": 7.574,
+      "eval_runtime": 2.1036,
+      "eval_samples_per_second": 6.18,
+      "eval_steps_per_second": 6.18,
       "step": 1
     },
     {
       "epoch": 0.008403361344537815,
-      "grad_norm": 8.62297248840332,
+      "grad_norm": 8.523767471313477,
       "learning_rate": 4e-05,
       "loss": 1.5244,
       "step": 2
     },
     {
       "epoch": 0.012605042016806723,
-      "grad_norm": 4.18648099899292,
+      "grad_norm": 4.048158645629883,
       "learning_rate": 6e-05,
-      "loss": 1.0555,
+      "loss": 1.0561,
       "step": 3
     },
     {
       "epoch": 0.012605042016806723,
-      "eval_loss": 1.1284071207046509,
-      "eval_runtime": 1.7128,
-      "eval_samples_per_second": 7.59,
-      "eval_steps_per_second": 7.59,
+      "eval_loss": 1.1272711753845215,
+      "eval_runtime": 2.086,
+      "eval_samples_per_second": 6.232,
+      "eval_steps_per_second": 6.232,
       "step": 3
-    },
-    {
-      "epoch": 0.01680672268907563,
-      "grad_norm": 4.5825982093811035,
-      "learning_rate": 8e-05,
-      "loss": 1.0671,
-      "step": 4
-    },
-    {
-      "epoch": 0.02100840336134454,
-      "grad_norm": 4.389379024505615,
-      "learning_rate": 0.0001,
-      "loss": 0.8529,
-      "step": 5
-    },
-    {
-      "epoch": 0.025210084033613446,
-      "grad_norm": 4.5690016746521,
-      "learning_rate": 0.00012,
-      "loss": 0.7349,
-      "step": 6
-    },
-    {
-      "epoch": 0.025210084033613446,
-      "eval_loss": 0.6369205117225647,
-      "eval_runtime": 1.7187,
-      "eval_samples_per_second": 7.564,
-      "eval_steps_per_second": 7.564,
-      "step": 6
-    },
-    {
-      "epoch": 0.029411764705882353,
-      "grad_norm": 3.573637008666992,
-      "learning_rate": 0.00014,
-      "loss": 0.6098,
-      "step": 7
-    },
-    {
-      "epoch": 0.03361344537815126,
-      "grad_norm": 4.503354072570801,
-      "learning_rate": 0.00016,
-      "loss": 0.4159,
-      "step": 8
-    },
-    {
-      "epoch": 0.037815126050420166,
-      "grad_norm": 2.6465718746185303,
-      "learning_rate": 0.00018,
-      "loss": 0.1273,
-      "step": 9
-    },
-    {
-      "epoch": 0.037815126050420166,
-      "eval_loss": 0.05756353586912155,
-      "eval_runtime": 1.7191,
-      "eval_samples_per_second": 7.562,
-      "eval_steps_per_second": 7.562,
-      "step": 9
-    },
-    {
-      "epoch": 0.04201680672268908,
-      "grad_norm": 2.1379239559173584,
-      "learning_rate": 0.0002,
-      "loss": 0.0709,
-      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -123,12 +58,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 115436704235520.0,
+  "total_flos": 34631011270656.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57b896ab5add319c7a3d7a1630c80773e133821fa946fe384bc346f8d303f32c
+oid sha256:592d3f15b668ad02f635996ffd86b23cd3af5f8508df3ef568348db663779af9
 size 6776